© 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. 221933
    Prev
    Next
    INDEX
    Explanations

    legal protection

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

    foreign residents

    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
    sensor
    0.47
     особен
    0.46
    ொண்டு
    0.46
     PRESENT
    0.46
     recharged
    0.46
     consumables
    0.46
    🏜
    0.45
    ChessBot
    0.45
    থেকে
    0.45
     GES
    0.45
    POSITIVE LOGITS
    2
    0.48
     trow
    0.48
    尹
    0.45
    راط
    0.43
    阁
    0.43
    란
    0.42
    哽
    0.41
    アイ
    0.40
     Kirby
    0.40
     throwing
    0.40
    Activations Density 0.001%

    No Known Activations