© 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. 153674
    Prev
    Next
    INDEX
    Explanations

    best insurance options

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

    specific actions and details

    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
    commonly
    0.49
    ين
    0.48
     பல்கலைக்கழக
    0.48
     細胞
    0.48
     انس
    0.48
     यूनाइटेड
    0.47
     silber
    0.47
    開
    0.47
    inline
    0.46
     பி
    0.46
    POSITIVE LOGITS
    [
    0.53
    Tour
    0.52
    a
    0.49
    '
    0.47
     Tour
    0.45
    v
    0.44
    ,
    0.43
    <
    0.43
    i
    0.43
     Lost
    0.42
    Activations Density 0.002%

    No Known Activations