© 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. 243106
    Prev
    Next
    INDEX
    Explanations

    flow control

    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
     хора
    0.49
     哦
    0.49
     ഭ
    0.48
     Quite
    0.47
     Apakah
    0.47
     ფ
    0.47
     感じ
    0.47
     ይ
    0.46
     fah
    0.46
    smanship
    0.46
    POSITIVE LOGITS
    赘
    0.50
    toInt
    0.47
    patches
    0.47
     coerc
    0.46
    2
    0.46
    十三
    0.46
    属性
    0.45
    十四
    0.44
     coercion
    0.44
    对抗
    0.44
    Activations Density 0.000%

    No Known Activations