© 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. 22-GEMMASCOPE-RES-131K
    7. 72737
    Prev
    Next
    INDEX
    Explanations

    pharmacokinetics and biofeedback

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

    numeric values or measurements in technical texts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     more
    -1.37
     all
    -1.10
    Other
    -1.09
     this
    -1.08
     before
    -1.07
     what
    -1.05
     October
    -1.05
    For
    -1.04
     More
    -1.04
     every
    -1.02
    POSITIVE LOGITS
     geene
    1.12
    unile
    1.06
     soooo
    1.05
     ALREADY
    1.02
    Hmmm
    1.02
     terrific
    1.00
     sooo
    0.99
    INSTRUCTIONS
    0.98
    ᵤ
    0.98
     AMAZING
    0.98
    Activations Density 0.000%

    No Known Activations