© 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. 185038
    Prev
    Next
    INDEX
    Explanations

    created you, coming, side effects, two year, national, him

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

    non-English characters

    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
    lable
    0.46
    sales
    0.45
    grid
    0.44
    opp
    0.44
    labels
    0.44
    s
    0.44
    economic
    0.42
     racial
    0.41
    racial
    0.41
    label
    0.41
    POSITIVE LOGITS
    Ми
    0.55
    Φ
    0.55
    Мі
    0.52
    ιού
    0.51
     μεγαλύτε
    0.50
    सेन
    0.50
     considérons
    0.50
     pensato
    0.50
    istä
    0.50
    Ψ
    0.49
    Activations Density 0.000%

    No Known Activations