© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 155577
    Prev
    Next
    INDEX
    Explanations

    response and action

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

    originality, correct, plan documents

    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
     infants
    0.48
    ivation
    0.48
    </td>
    0.48
    reich
    0.48
    ination
    0.47
    াকর
    0.47
     Gep
    0.47
     eccentricity
    0.47
    ]);
    0.45
     monarchs
    0.44
    POSITIVE LOGITS
     delle
    0.44
     aihe
    0.44
    ÁN
    0.43
     denken
    0.42
    意识到
    0.42
     répond
    0.41
    发生的
    0.41
    ায়ী
    0.40
    响应文件
    0.40
     নেট
    0.40
    Activations Density 0.000%

    No Known Activations