© 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. 208710
    Prev
    Next
    INDEX
    Explanations

    collaboration and semantic data

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

    explaining context variations

    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
    考え
    0.52
     scrollBody
    0.52
    梸
    0.52
     রয়ে
    0.49
     Calcul
    0.47
     ক্লিক
    0.47
     গাড়ি
    0.47
    啮
    0.47
     обсужда
    0.46
    𝒗
    0.46
    POSITIVE LOGITS
    ad
    0.62
    ub
    0.50
    asers
    0.50
     rehearsals
    0.49
    aff
    0.46
     affer
    0.46
    lock
    0.45
    fer
    0.45
    blue
    0.45
    folk
    0.45
    Activations Density 0.001%

    No Known Activations