© 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. 172168
    Prev
    Next
    INDEX
    Explanations

    not act

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

    conversational punctuation

    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
    ciencia
    0.55
    ’
    0.52
     prophecies
    0.49
     ‚
    0.49
     Reasoning
    0.48
    wać
    0.47
     menyampaikan
    0.47
     mengadakan
    0.46
    where
    0.45
     medals
    0.45
    POSITIVE LOGITS
    ंधरा
    0.47
     jsx
    0.47
    Mood
    0.45
    可能
    0.43
     Mood
    0.43
     liệt
    0.43
    ಬ್ಬಿಣ
    0.42
    勖
    0.41
     пе
    0.41
    无论
    0.41
    Activations Density 0.001%

    No Known Activations