© 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. 105944
    Prev
    Next
    INDEX
    Explanations

    recommending the service

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

    parenthesized phrases

    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
     afternoon
    0.41
    呎
    0.41
    waitTime
    0.40
    基地
    0.40
    至少
    0.39
    CAPTURE
    0.39
    thisTrack
    0.38
     hou
    0.38
     DeL
    0.37
     Hou
    0.37
    POSITIVE LOGITS
     morphology
    0.40
    독
    0.39
     seguimos
    0.38
     독
    0.38
    ige
    0.38
     Morphology
    0.38
    glial
    0.37
     uniqueness
    0.36
     emerges
    0.36
     изготов
    0.36
    Activations Density 0.001%

    No Known Activations