© 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. 27103
    Prev
    Next
    INDEX
    Explanations

    first-class, first-hand, first aid

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

    first + word

    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
    \
    0.91
    '
    0.75
    .
    0.70
    :
    0.67
     νέ
    0.61
    (
    0.60
     zim
    0.58
    \})
    0.57
    ?
    0.56
    rof
    0.55
    POSITIVE LOGITS
     First
    1.13
    first
    1.09
    getFirst
    0.99
    FIRST
    0.90
     first
    0.88
     Primeira
    0.88
     FIRST
    0.88
     Первая
    0.87
    प्रथम
    0.86
     responders
    0.84
    Activations Density 0.090%

    No Known Activations