© 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. 190216
    Prev
    Next
    INDEX
    Explanations

    legal terms or professional contexts

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

    french toast, checking, election, current sources, robotic, list builder

    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
     테
    0.50
     ग्र
    0.50
     MAD
    0.49
     ẞ
    0.49
     우
    0.48
     Ә
    0.47
     misch
    0.46
     판
    0.45
     பகுதிகளில்
    0.45
     deut
    0.45
    POSITIVE LOGITS
    Actors
    0.47
    लीवुड
    0.46
    文学
    0.45
    രേ
    0.43
    ঘুম
    0.43
    ို့
    0.42
     hiyo
    0.42
     hilo
    0.42
     phenomenal
    0.42
     mapa
    0.41
    Activations Density 0.000%

    No Known Activations