© 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. 244228
    Prev
    Next
    INDEX
    Explanations

    supply

    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
    collectionView
    0.51
     পরবর্ত
    0.46
     ဂ
    0.46
     紅
    0.46
     thời
    0.45
     圆
    0.44
    つなが
    0.44
    ジュエリー
    0.43
    чат
    0.43
     टमाटर
    0.43
    POSITIVE LOGITS
    :
    0.53
     legisl
    0.44
    lessness
    0.40
    :#
    0.40
    ?
    0.40
    gathering
    0.39
     alapján
    0.39
     postulate
    0.39
    T
    0.39
    糹
    0.38
    Activations Density 0.001%

    No Known Activations