© 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. 12353
    Prev
    Next
    INDEX
    Explanations

    implementing changes, measures, and systems

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

    implementing things

    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
     ಹೆಸರು
    0.63
     mieście
    0.59
    paragus
    0.58
    tsprec
    0.57
     ምስ
    0.57
     ಹೆಸ
    0.55
    𒈬
    0.55
     질문
    0.54
     も
    0.54
    𒀝
    0.54
    POSITIVE LOGITS
     Implementing
    0.76
     Implement
    0.74
    Implementing
    0.73
    0
    0.72
    实施
    0.68
     implement
    0.68
     implementations
    0.67
    Implement
    0.64
     implements
    0.64
    implement
    0.64
    Activations Density 0.070%

    No Known Activations