© 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. 128864
    Prev
    Next
    INDEX
    Explanations

    the (followed by noun)

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     also
    -1.15
     can
    -1.14
     évêque
    -1.12
     always
    -1.09
     could
    -1.06
    "،
    -1.02
     if
    -1.00
     before
    -0.99
     will
    -0.96
    日本では
    -0.94
    POSITIVE LOGITS
     to
    1.32
    proses
    1.09
     situation
    1.05
     solches
    1.04
     нынеш
    1.02
     resultant
    1.00
    mètre
    1.00
     as
    1.00
    ването
    0.99
     contribution
    0.97
    Activations Density 0.035%

    No Known Activations