© 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. 139367
    Prev
    Next
    INDEX
    Explanations

    profiles and contact details

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

    take your, you want, time durations

    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
     I
    0.52
     Moran
    0.46
    <0x9E>
    0.46
     disease
    0.45
    buscar
    0.44
    SAN
    0.44
    alysis
    0.43
     allyl
    0.43
     buscar
    0.42
     tolerance
    0.42
    POSITIVE LOGITS
    련
    0.50
    ১৭
    0.48
    heits
    0.47
    듕
    0.47
    полни
    0.47
    ismillahirrah
    0.46
     бъ
    0.46
     quotidienne
    0.46
    rać
    0.46
     уров
    0.45
    Activations Density 0.001%

    No Known Activations