© 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. 238026
    Prev
    Next
    INDEX
    Explanations

    listings with specific details

    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
     Sure
    0.46
    !');
    0.45
    sure
    0.44
     Dorm
    0.42
    Sure
    0.41
    yong
    0.41
    Johnny
    0.41
    ರ್ಯ
    0.40
    풉
    0.40
    ਜ਼
    0.40
    POSITIVE LOGITS
     saling
    0.48
     ВИ
    0.47
    BadRequest
    0.46
     situado
    0.46
     フランス
    0.45
     获取
    0.45
     बौद्ध
    0.45
     смогли
    0.45
     一个
    0.45
     reciting
    0.44
    Activations Density 0.002%

    No Known Activations