© 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. 144608
    Prev
    Next
    INDEX
    Explanations

    common words followed by specific words

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

    working with diversity

    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
     integrand
    0.45
    옴
    0.44
    각
    0.43
    在
    0.42
     covariance
    0.42
     egreg
    0.42
     occurrence
    0.42
     incident
    0.41
    occurrence
    0.41
    spanning
    0.41
    POSITIVE LOGITS
     nejen
    0.56
     bör
    0.52
     bringt
    0.52
    !
    0.49
     ál
    0.48
    !।
    0.47
    !,
    0.47
    !.
    0.46
    ⛽
    0.46
    🥇
    0.46
    Activations Density 0.001%

    No Known Activations