© 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. 106187
    Prev
    Next
    INDEX
    Explanations

    specific entities and product names

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

    foreign characters and words

    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
    Compressed
    0.46
    Administ
    0.44
    ت
    0.43
    murder
    0.43
     apt
    0.42
    امي
    0.42
    Supplier
    0.42
    ✵
    0.42
     مدير
    0.41
    schools
    0.41
    POSITIVE LOGITS
    宏
    0.49
    栄
    0.48
    꼭
    0.48
     trabajar
    0.48
    <0xE9>
    0.46
    ieron
    0.46
    カラ
    0.46
     trabaja
    0.46
     reiniciar
    0.46
    べ
    0.46
    Activations Density 0.000%

    No Known Activations