© 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. 229466
    Prev
    Next
    INDEX
    Explanations

    photographic, university, similar activity

    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
     espace
    0.52
     lysate
    0.49
     intestin
    0.49
     vírus
    0.49
    ৤
    0.49
     alimentation
    0.48
     contesto
    0.47
     espaço
    0.46
     coordenada
    0.46
     dryness
    0.46
    POSITIVE LOGITS
    0.59
    p
    0.58
    t
    0.50
    d
    0.49
    l
    0.49
    Encycl
    0.48
    s
    0.47
    UN
    0.46
    PI
    0.46
    b
    0.46
    Activations Density 0.000%

    No Known Activations