© 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. 39164
    Prev
    Next
    INDEX
    Explanations

    California

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

    California and associated contexts

    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
     límites
    0.46
     verdes
    0.44
     Badajoz
    0.44
     朝
    0.44
     കാല
    0.43
     ওয়
    0.43
     zerstört
    0.42
     engulfed
    0.42
     clickView
    0.42
     ಕಾಲ
    0.42
    POSITIVE LOGITS
    '
    0.59
    _
    0.52
    ingly
    0.49
    特性
    0.48
    は
    0.48
    isering
    0.46
    ₓ
    0.45
    AMPLE
    0.44
     honing
    0.44
    巨大
    0.43
    Activations Density 0.000%

    No Known Activations