© 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. 16197
    Prev
    Next
    INDEX
    Explanations

    documentation and code examples

    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
     in
    -1.83
    Despite
    -1.80
     by
    -1.79
     because
    -1.76
    With
    -1.75
     what
    -1.69
    Without
    -1.67
    Several
    -1.67
    when
    -1.66
     despite
    -1.62
    POSITIVE LOGITS
     momentous
    1.84
     somewhat
    1.84
     semelh
    1.82
     magnificent
    1.77
     splendid
    1.76
     wondrous
    1.76
     delightfully
    1.76
     insanely
    1.74
     horrifying
    1.73
     decidedly
    1.71
    Activations Density 0.000%

    No Known Activations