© 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. 11803
    Prev
    Next
    INDEX
    Explanations

    chatbots and prompts

    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
     एमसीक्यू
    0.56
    丳
    0.52
     الضرب
    0.48
    䧉
    0.47
     записа
    0.46
    स्‍
    0.46
    آ
    0.46
    displaystyle
    0.46
     Leighton
    0.46
    篂
    0.46
    POSITIVE LOGITS
     supports
    0.53
     services
    0.52
     bonuses
    0.52
     mascot
    0.50
     service
    0.50
     logo
    0.49
     služby
    0.47
    服务
    0.47
     servizio
    0.46
     pace
    0.46
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.