© 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. 33226
    Prev
    Next
    INDEX
    Explanations

    secret plots and intrigue

    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
     so
    -2.66
     for
    -2.53
     at
    -2.45
     in
    -2.41
     on
    -2.34
     because
    -2.30
     often
    -2.25
     usually
    -2.25
     as
    -2.19
     four
    -2.17
    POSITIVE LOGITS
     faciliter
    2.02
     corriger
    1.95
    튿
    1.94
    ఽ
    1.92
     verhind
    1.90
     zoude
    1.85
    ඈ
    1.79
     applau
    1.79
     participer
    1.78
     herbes
    1.77
    Activations Density 0.085%

    No Known Activations