© 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. 59583
    Prev
    Next
    INDEX
    Explanations

    is available / narrow / complex

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

    while, depending on

    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
     Pyaar
    0.55
     Epile
    0.50
     Redmi
    0.47
     ७
    0.46
    5
    0.46
    <0xB3>
    0.46
     Euph
    0.46
    ٧
    0.45
     https
    0.45
    aes
    0.45
    POSITIVE LOGITS
    jobNumber
    0.49
    '/
    0.48
    セミナー
    0.48
    '}}>
    0.47
    '?
    0.47
     людям
    0.46
    '&
    0.46
    lblCredits
    0.46
     सला
    0.46
     люди
    0.45
    Activations Density 0.000%

    No Known Activations