© 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-3-4B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 6235
    Prev
    Next
    INDEX
    Explanations

    intense and severe effects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_17_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    glich
    2.11
     reten
    1.98
    isches
    1.93
    ྀ
    1.93
    러
    1.90
    lation
    1.90
    𝗛
    1.90
    sche
    1.88
     extensible
    1.88
    ⃣
    1.87
    POSITIVE LOGITS
    犸
    2.89
    у
    2.43
    в
    2.34
    ट
    2.30
    烈的
    2.24
    weixin
    2.16
     scrutiny
    2.10
    fehlung
    1.99
    렬
    1.99
    ва
    1.96
    Activations Density 0.258%

    No Known Activations