© 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. 99466
    Prev
    Next
    INDEX
    Explanations

    furniture, faculty, support, practices

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

    self-harm, code block, travel, joke

    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
    мат
    0.53
    𝚑
    0.49
    ミュージ
    0.47
    振り返
    0.46
    脇
    0.46
    زندگی
    0.45
     Anosov
    0.45
    後ろ
    0.45
    プレイ
    0.45
     młod
    0.44
    POSITIVE LOGITS
    w
    0.56
    on
    0.50
    ap
    0.50
    oo
    0.50
    en
    0.50
     Rank
    0.50
     Furniture
    0.48
    b
    0.48
    s
    0.48
    W
    0.48
    Activations Density 0.000%

    No Known Activations