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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 82348
    Prev
    Next
    INDEX
    Explanations

    preservation and cryopreservation

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

    technical text related to biological specimens and preservation methods.

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

    The main thing this neuron does is spot numeric tokens and quantitative values (e.g. years, measurements, counts).

    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
    ggior
    -0.91
     papaya
    -0.81
    Collateral
    -0.75
    ggiata
    -0.74
    葡萄
    -0.72
     avocados
    -0.70
    彙
    -0.69
     coriander
    -0.69
    陋
    -0.68
     voorzien
    -0.66
    POSITIVE LOGITS
     preserved
    3.84
     preservation
    3.19
    preserved
    3.06
     dried
    2.83
     preserve
    2.81
     preserving
    2.75
     preserves
    2.59
     Preservation
    2.50
    preservation
    2.45
    preserve
    2.39
    Activations Density 0.094%

    No Known Activations