© 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. 9083
    Prev
    Next
    INDEX
    Explanations

    following numbers and names

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

    strategic circumstances

    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
    ets
    0.55
    );
    0.51
    "
    0.50
    est
    0.50
    ents
    0.50
    ened
    0.48
    æ
    0.48
    etting
    0.47
    ivari
    0.47
    `
    0.46
    POSITIVE LOGITS
    缃
    0.50
     يك
    0.48
    निश्
    0.47
     Municipality
    0.47
     Samoa
    0.47
    郓
    0.47
     Komitet
    0.47
    ायत
    0.46
    还是
    0.46
     سلطان
    0.46
    Activations Density 0.000%

    No Known Activations