© 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. 28195
    Prev
    Next
    INDEX
    Explanations

    specific items or concepts

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

    UK considers, believe a, required unless

    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
     Wrapper
    0.46
     CENT
    0.44
     झ
    0.43
     Sé
    0.43
     Callback
    0.43
     barras
    0.43
     來
    0.42
    噠
    0.42
    .}}
    0.42
     Cous
    0.42
    POSITIVE LOGITS
    ancang
    0.49
    ுமா
    0.49
    药物
    0.48
    ையோ
    0.48
    つき
    0.45
    ამდ
    0.45
    дете
    0.44
    时间的
    0.44
    glacial
    0.44
    чната
    0.44
    Activations Density 0.000%

    No Known Activations