© 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. 137134
    Prev
    Next
    INDEX
    Explanations

    Personally Identifiable Information

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

    action-oriented descriptions

    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
    TextureData
    0.55
    хран
    0.53
    幸せ
    0.52
     pronunci
    0.50
     যে
    0.50
     చేరు
    0.49
    恙
    0.49
     precedente
    0.47
     दिव्य
    0.47
     функции
    0.46
    POSITIVE LOGITS
     REPORTS
    0.48
     MY
    0.45
     reports
    0.43
    äll
    0.43
     olt
    0.43
     REP
    0.42
    came
    0.41
    uchten
    0.41
     ī
    0.41
     INC
    0.41
    Activations Density 0.001%

    No Known Activations