© 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. 207822
    Prev
    Next
    INDEX
    Explanations

    specific words followed by related actions or continuations

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

    phrases starting with prepositions and time

    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
    Negative Logits
     Policing
    0.41
     Colleges
    0.40
     Supply
    0.39
     तहसील
    0.38
     Ahead
    0.38
     Landmarks
    0.38
    Ⓡ
    0.38
     State
    0.38
     naming
    0.38
    stech
    0.38
    POSITIVE LOGITS
    𝚓
    0.54
    ။
    0.54
    <unused1060>
    0.50
    φων
    0.50
    <unused336>
    0.49
     compromiso
    0.48
     горо
    0.48
    ει
    0.47
     agrupación
    0.47
     ηλεκ
    0.47
    Activations Density 0.001%

    No Known Activations