© 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. 116575
    Prev
    Next
    INDEX
    Explanations

    especially

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

    beach road

    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
     differed
    0.43
     had
    0.42
     степень
    0.42
    꼐
    0.42
    אה
    0.42
     prevented
    0.41
    гром
    0.41
     estavam
    0.41
     Dryer
    0.41
    FromThe
    0.41
    POSITIVE LOGITS
     特に
    0.46
    <0xE9>
    0.45
    人は
    0.45
    例えば
    0.45
    特に
    0.44
    チャ
    0.43
     Gloria
    0.43
    <0x86>
    0.42
     insbesondere
    0.42
    occas
    0.42
    Activations Density 0.001%

    No Known Activations