© 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. 175960
    Prev
    Next
    INDEX
    Explanations

    to provide repair

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

    special treatment and permits

    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
     ป
    0.48
     Danilo
    0.48
    LARGE
    0.48
     ប
    0.46
    OHAMA
    0.46
     anual
    0.46
     бо
    0.45
     Bonner
    0.44
     വാക്ക
    0.44
     Medicina
    0.44
    POSITIVE LOGITS
     supporting
    0.52
    ーズ
    0.52
    リーム
    0.46
     resisting
    0.46
     apoyar
    0.46
    supporting
    0.44
    ライス
    0.43
     ise
    0.43
    べ
    0.42
    える
    0.42
    Activations Density 0.001%

    No Known Activations