© 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. 242163
    Prev
    Next
    INDEX
    Explanations

    leave a responsesubscribe

    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
    ServiceObject
    0.41
    ОР
    0.40
    基
    0.39
    を開始
    0.38
    েক্টর
    0.38
    WholeProgram
    0.37
    тила
    0.37
    CENTR
    0.37
    じめ
    0.36
    رح
    0.36
    POSITIVE LOGITS
     hậu
    0.45
     Mano
    0.44
     dren
    0.42
    ⚠️
    0.42
     နောက်
    0.40
     Ibid
    0.40
     للب
    0.40
    <unused262>
    0.40
     dolor
    0.40
     ответственность
    0.40
    Activations Density 0.001%

    No Known Activations