© 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. 64840
    Prev
    Next
    INDEX
    Explanations

    implementation minus, climbed about

    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
    髋
    -1.05
    probably
    -1.05
    ţin
    -1.05
    perhaps
    -0.98
    皷
    -0.94
    ßt
    -0.94
    presumably
    -0.93
     ـ
    -0.93
     quirks
    -0.93
    Œ
    -0.92
    POSITIVE LOGITS
     during
    1.10
     gave
    1.03
     went
    1.02
     then
    1.02
    ．．．
    0.99
     including
    0.98
     will
    0.98
     became
    0.96
     specially
    0.96
     took
    0.93
    Activations Density 0.066%

    No Known Activations