© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 34189
    Prev
    Next
    INDEX
    Explanations

    following articles and adjectives

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

    abstract concepts or actions

    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
    ﺲ
    0.46
    بری
    0.46
    accion
    0.44
     Gesù
    0.44
    영
    0.44
    arrêt
    0.42
    ลำ
    0.42
    량
    0.42
    जों
    0.42
    éticos
    0.41
    POSITIVE LOGITS
     Drawable
    0.46
     (\%)
    0.45
     соста
    0.44
     ordination
    0.44
    olipid
    0.44
     Approximate
    0.43
     groupBy
    0.43
    Ⲛ
    0.43
    फिल
    0.43
    น
    0.43
    Activations Density 0.000%

    No Known Activations