© 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. 166258
    Prev
    Next
    INDEX
    Explanations

    organizations and associations

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

    film minimization, related needs

    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
    눴
    0.55
    ㊙
    0.51
    倠
    0.48
    日に
    0.48
    マネ
    0.46
    ㎜
    0.46
    ⑫
    0.46
    <unused2168>
    0.46
    ようになって
    0.46
    🗻
    0.46
    POSITIVE LOGITS
    蜕
    0.47
    OR
    0.46
     Awards
    0.45
     Assumptions
    0.44
    z
    0.44
    Assumption
    0.44
    rap
    0.43
    (
    0.43
    ai
    0.42
     coins
    0.42
    Activations Density 0.001%

    No Known Activations