© 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. 71511
    Prev
    Next
    INDEX
    Explanations

    original concepts and origins

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

    unique twist

    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
     పరీ
    0.45
     controlado
    0.44
    in
    0.44
    StillWater
    0.44
    äter
    0.43
     завдання
    0.43
     変
    0.43
     Rip
    0.43
     Variance
    0.43
     神
    0.42
    POSITIVE LOGITS
    ג
    0.53
    ުޅ
    0.51
    持有
    0.48
    لال
    0.48
    يته
    0.46
     centru
    0.45
    رج
    0.45
    رخ
    0.44
    ალაქ
    0.43
    اج
    0.43
    Activations Density 0.000%

    No Known Activations