© 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. 240763
    Prev
    Next
    INDEX
    Explanations

    from X

    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
     antigüedad
    0.50
    निक
    0.46
    jwa
    0.46
    iaan
    0.46
    ⤟
    0.46
    ग्रह
    0.45
     glist
    0.44
     ambiguities
    0.44
    ❆
    0.44
    выше
    0.43
    POSITIVE LOGITS
     servo
    0.45
    儲
    0.45
    諮
    0.44
    溲
    0.44
     والط
    0.43
    ルメ
    0.43
    音
    0.43
    免費
    0.43
    ニメ
    0.42
    getStudentNo
    0.42
    Activations Density 0.001%

    No Known Activations