© 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. 219706
    Prev
    Next
    INDEX
    Explanations

    face to face

    np_acts-logits-general · gemini-2.5-flash-lite

    people and places

    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
     can
    0.55
    hv
    0.54
     genetic
    0.46
    t
    0.46
    导致
    0.45
    routine
    0.45
    command
    0.44
    genetic
    0.44
    robots
    0.42
     PUT
    0.42
    POSITIVE LOGITS
     సంగీ
    0.55
     Hendrik
    0.55
    멕
    0.52
    벧
    0.49
    룔
    0.48
    ಿಣ
    0.48
    νος
    0.48
     చెప్పారు
    0.47
    쾰
    0.47
     儿
    0.47
    Activations Density 0.000%

    No Known Activations