© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 117929
    Prev
    Next
    INDEX
    Explanations

    California

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

    US states

    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
    Negative Logits
     ແລະ
    0.64
     وطن
    0.63
    ينه
    0.60
    
    0.59
    인이
    0.58
     طويل
    0.58
     الآخر
    0.57
    페
    0.57
    𝙩
    0.57
     페
    0.57
    POSITIVE LOGITS
    s
    0.82
    r
    0.72
    b
    0.71
    a
    0.71
    q
    0.70
    o
    0.65
    _
    0.64
    State
    0.63
     State
    0.62
    ↵↵
    0.60
    Activations Density 0.058%

    No Known Activations