© 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. 19435
    Prev
    Next
    INDEX
    Explanations

    punctuation, Peter, Samsung

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

    concave lens

    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
    ंडीज
    0.48
    ネルギー
    0.48
    イド
    0.47
    ることが
    0.47
    FlashValue
    0.46
     abducted
    0.46
    形成
    0.46
    ರ
    0.46
    стой
    0.46
    вших
    0.46
    POSITIVE LOGITS
    UR
    0.48
     Martini
    0.44
     فيما
    0.43
    nh
    0.42
    ui
    0.42
    anks
    0.42
    em
    0.41
     I
    0.40
    èg
    0.40
    gi
    0.40
    Activations Density 0.000%

    No Known Activations