© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 39380
    Prev
    Next
    INDEX
    Explanations

    specific sequences of words

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

    tales, script, destinations, supporting

    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
    ib
    0.54
    enean
    0.51
    ə
    0.50
    ī
    0.49
    tem
    0.49
    emailer
    0.48
    abileceğ
    0.48
     சட்டமன்ற
    0.47
    iam
    0.46
    inqu
    0.46
    POSITIVE LOGITS
    י
    0.54
    秕
    0.50
    卅
    0.50
    ర్
    0.48
     pij
    0.48
    艋
    0.47
     EAST
    0.46
     PIPE
    0.46
     meio
    0.46
    逺
    0.46
    Activations Density 0.000%

    No Known Activations