© 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. 11882
    Prev
    Next
    INDEX
    Explanations

    essential followed by categorized nouns

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

    essential requirements

    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
    '
    0.70
    ен
    0.59
    ્સ
    0.59
    ეფ
    0.59
    <0xAC>
    0.59
    ем
    0.57
    ない
    0.56
    ಸ
    0.56
     Spearman
    0.56
    \
    0.55
    POSITIVE LOGITS
     essential
    1.19
     필수
    1.16
    essential
    1.09
     Essential
    1.05
     essentials
    1.05
     esenciales
    0.95
    Essential
    0.93
     ضروری
    0.93
    ro
    0.92
    necessary
    0.91
    Activations Density 0.038%

    No Known Activations