© 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. 110080
    Prev
    Next
    INDEX
    Explanations

    pronoun followed by verb or phrase

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

    whats / lets / don't / won't

    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
    a
    1.04
    ה
    0.89
    к
    0.82
    ту
    0.80
     is
    0.79
    я
    0.77
    し
    0.77
    ла
    0.76
     of
    0.76
     has
    0.76
    POSITIVE LOGITS
    洺
    0.63
    voud
    0.60
    nieuw
    0.60
    jük
    0.59
    bbero
    0.59
    avano
    0.59
    س
    0.59
     โ
    0.58
    alakip
    0.58
     یعنی
    0.58
    Activations Density 0.435%

    No Known Activations