© 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. 168906
    Prev
    Next
    INDEX
    Explanations

    recruiting visiting creating

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

    perspectives and states

    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
     ሌሎች
    0.47
     जलदाय
    0.43
    댜
    0.41
     higiene
    0.40
     contaminants
    0.40
     Jacobsen
    0.40
    dough
    0.40
     поступ
    0.40
     biochem
    0.40
     화학
    0.39
    POSITIVE LOGITS
     bulunduğu
    0.48
    মনের
    0.47
    ☚
    0.46
     Visiting
    0.45
     Recruiting
    0.45
    为
    0.44
    ्यु
    0.44
    ⇜
    0.44
    觐
    0.43
    用于
    0.43
    Activations Density 0.001%

    No Known Activations