© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 63351
    Prev
    Next
    INDEX
    Explanations

    cryo-preservation

    np_acts-logits-general · gemini-2.5-flash-lite

    concepts related to freezing, preservation, or cryogenic processes.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron is highly responsive to terms related to cryogenic freezing and suspended‐animation processes.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cleared
    -1.33
    Clearing
    -1.23
    clearing
    -1.20
     cleared
    -1.19
     Clearing
    -1.18
     clears
    -1.17
     clearing
    -1.13
     clearance
    -1.09
    clearance
    -1.02
     Clearance
    -0.98
    POSITIVE LOGITS
     cry
    1.52
     frozen
    1.47
     cryo
    1.41
     pod
    1.34
     pods
    1.32
     suspended
    1.24
     preservation
    1.23
     hibernation
    1.22
     capsule
    1.22
     freezing
    1.22
    Activations Density 0.019%

    No Known Activations