© 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. 111104
    Prev
    Next
    INDEX
    Explanations

    a verb followed by punctuation

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

    introducing actions or goals

    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
    পি
    0.52
    acara
    0.50
    피
    0.49
    사람
    0.49
    fabrik
    0.49
    писа
    0.48
    тури
    0.48
    чора
    0.48
    불
    0.48
    फ
    0.47
    POSITIVE LOGITS
     autonomy
    0.56
     gradual
    0.54
     pots
    0.52
     learned
    0.52
     sullen
    0.50
     numbers
    0.50
     salts
    0.49
     shading
    0.49
     frantic
    0.48
     absolut
    0.48
    Activations Density 0.000%

    No Known Activations