© 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. 72065
    Prev
    Next
    INDEX
    Explanations

    words starting with h

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

    hack, HTML, hire, height

    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
    is
    1.58
    as
    1.10
    ur
    1.00
     or
    0.96
    나
    0.93
    この
    0.91
    ０
    0.91
    at
    0.90
     as
    0.90
    iselt
    0.89
    POSITIVE LOGITS
    ס
    1.08
    دين
    0.99
    ен
    0.99
    pital
    0.90
    ال
    0.89
    ал
    0.88
    жим
    0.87
    "]}
    0.85
    ’
    0.84
    ")]
    0.82
    Activations Density 1.596%

    No Known Activations