© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 237580
    Prev
    Next
    INDEX
    Explanations

    in conjunction with other

    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
    。.
    0.44
    渠
    0.44
    _
    0.43
    行動
    0.43
    年月日
    0.42
    팥
    0.42
    行动
    0.41
    しておく
    0.41
     appendices
    0.41
     antis
    0.40
    POSITIVE LOGITS
     caratteristiche
    0.52
     ugu
    0.49
     wọn
    0.49
     Під
    0.49
    CTURE
    0.48
     ຊ
    0.48
     zählt
    0.47
     நான்
    0.47
     முறை
    0.47
     temperatura
    0.46
    Activations Density 0.000%

    No Known Activations