© 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. 182445
    Prev
    Next
    INDEX
    Explanations

    music and other cultural content

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

    loading, search, tax preparation

    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
    ๙
    0.53
     hearsay
    0.48
    ๘
    0.46
     budd
    0.45
     patern
    0.43
     folgender
    0.42
     марке
    0.42
    の良い
    0.41
     mlad
    0.41
    enb
    0.41
    POSITIVE LOGITS
    üş
    0.49
    ミ
    0.46
    fik
    0.45
     və
    0.45
     و
    0.44
     کی
    0.44
     서비스를
    0.43
    ş
    0.42
    ajas
    0.41
    Dequeue
    0.41
    Activations Density 0.000%

    No Known Activations