© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 1934
    Prev
    Next
    INDEX
    Explanations

    online estimate

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    действие
    0.49
     ainfi
    0.49
     señaló
    0.48
    íqu
    0.48
     เงี้ย
    0.47
    Benzoimidazol
    0.45
    <unused2197>
    0.45
    <unused2121>
    0.44
     randomNumber
    0.44
    WillAppear
    0.44
    POSITIVE LOGITS
    TAT
    0.49
    BED
    0.48
     gau
    0.48
     blueprint
    0.47
     demo
    0.46
    archi
    0.45
    openhagen
    0.45
     dine
    0.45
    cous
    0.44
    三种
    0.44
    Activations Density 0.003%

    No Known Activations