© 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. 60386
    Prev
    Next
    INDEX
    Explanations

    social media URLs

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

    related to parameters or code functions

    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
    راحی
    0.52
     whom
    0.48
     تبلی
    0.47
    )=\
    0.46
    den
    0.43
    য়া
    0.42
     عملی
    0.42
     یا
    0.42
     advertised
    0.42
     তোমাকে
    0.42
    POSITIVE LOGITS
    rá
    0.50
    טי
    0.46
     pú
    0.45
    ló
    0.45
    ن
    0.45
    ť
    0.45
    סטר
    0.44
    伊斯
    0.44
     készült
    0.44
    戶
    0.44
    Activations Density 0.000%

    No Known Activations