© 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. 187393
    Prev
    Next
    INDEX
    Explanations

    saving on materials and products

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

    this means, this one

    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
    is
    0.57
    id
    0.56
    Pine
    0.55
    de
    0.54
    un
    0.53
    em
    0.51
    Open
    0.51
    E
    0.50
    es
    0.50
    am
    0.50
    POSITIVE LOGITS
     ಮತ್ತೆ
    0.46
    리카
    0.45
    ходит
    0.45
     Kirsten
    0.44
     chống
    0.43
     éviter
    0.43
    ⇜
    0.43
    ?
    0.43
     AWAY
    0.43
     REALLY
    0.42
    Activations Density 0.001%

    No Known Activations