© 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. 34-GEMMASCOPE-RES-131K
    7. 77963
    Prev
    Next
    INDEX
    Explanations

    text following quote or delimiter

    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_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
     in
    -2.08
     at
    -1.97
     with
    -1.91
     as
    -1.85
     from
    -1.79
     without
    -1.65
     during
    -1.65
     if
    -1.63
     on
    -1.61
     because
    -1.59
    POSITIVE LOGITS
     gigantic
    1.84
     hugely
    1.82
     goofy
    1.81
     remarkably
    1.79
     extremely
    1.73
     lauded
    1.73
     relentless
    1.72
     myriad
    1.71
     whimsical
    1.68
     insanely
    1.66
    Activations Density 0.022%

    No Known Activations