© 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. 142970
    Prev
    Next
    INDEX
    Explanations

    followed by nouns or descriptions

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

    order, list, metaphor, growth

    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
    Multiple
    0.53
     Multiple
    0.52
     найбіль
    0.44
     Rhine
    0.43
    豐富
    0.42
    🥶
    0.41
    ORE
    0.41
     আন্দোল
    0.41
    カタログ
    0.41
    pread
    0.41
    POSITIVE LOGITS
    ằng
    0.51
    ğından
    0.48
     hacía
    0.48
    astaan
    0.47
    éssel
    0.46
    镓
    0.45
    abar
    0.44
    ancements
    0.44
     manuss
    0.44
    婵
    0.44
    Activations Density 0.001%

    No Known Activations