© 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. 33295
    Prev
    Next
    INDEX
    Explanations

    possibility and frequency

    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
     cerveau
    -1.30
    麃
    -1.24
    matitis
    -1.05
     احتم
    -1.04
    verter
    -1.02
     ส์
    -1.02
    ÑA
    -1.02
     ListView
    -1.02
    んでる
    -1.01
    Schicken
    -1.01
    POSITIVE LOGITS
     even
    1.63
     in
    1.36
     only
    1.31
     may
    1.28
     perhaps
    1.19
     indeed
    1.11
     geeigne
    1.08
     by
    1.04
     occasionally
    1.04
     altogether
    1.03
    Activations Density 0.039%

    No Known Activations