© 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. 66740
    Prev
    Next
    INDEX
    Explanations

    Interpreters, military reserve

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

    scene:

    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
     sir
    0.46
     cold
    0.45
     cavitation
    0.44
     land
    0.43
    বীন্দ্রনাথ
    0.42
     ({\
    0.42
     diseases
    0.42
     présente
    0.42
     defects
    0.41
    IZ
    0.41
    POSITIVE LOGITS
    女生
    0.46
     ومع
    0.43
     сотрудников
    0.42
     У
    0.42
     يلا
    0.42
     بم
    0.41
    性价比
    0.40
     مساء
    0.40
    girls
    0.40
     وت
    0.39
    Activations Density 0.000%

    No Known Activations