© 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. 22274
    Prev
    Next
    INDEX
    Explanations

    contact details and forms

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

    division and numbers

    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
    區域
    0.51
    咵
    0.47
     새
    0.46
     ይችላል
    0.45
    獰
    0.42
    ેચ્છ
    0.42
     mangiare
    0.42
    詑
    0.41
    っている
    0.41
     FOOD
    0.41
    POSITIVE LOGITS
    lN
    0.45
    lhe
    0.44
    *-
    0.41
    ds
    0.41
    le
    0.40
    lf
    0.39
    d
    0.39
    f
    0.39
    dv
    0.39
    disp
    0.39
    Activations Density 0.000%

    No Known Activations