© 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. 219196
    Prev
    Next
    INDEX
    Explanations

    restore data, using your, we often, chewers, in hybrid, Resolve Conflict

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

    covering potential benefits

    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
    洷
    0.44
    ä
    0.42
    ę
    0.42
    ื้อ
    0.42
    untut
    0.42
    шни
    0.41
     мероприя
    0.40
    걍
    0.40
    estial
    0.40
    ময়
    0.40
    POSITIVE LOGITS
     protons
    0.52
     conservatives
    0.46
     skrev
    0.46
     wrote
    0.45
     proton
    0.43
     |,
    0.43
    說
    0.42
     youll
    0.42
     precedenti
    0.42
     theres
    0.42
    Activations Density 0.002%

    No Known Activations