© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 81098
    Prev
    Next
    INDEX
    Explanations

    understanding and appreciation

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

    situational comedy

    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
    pressure
    0.43
    figured
    0.42
    াভাবিক
    0.42
    หุ้น
    0.40
    totals
    0.39
     pressures
    0.38
     acetyl
    0.38
    則
    0.38
     pressure
    0.37
    ायी
    0.37
    POSITIVE LOGITS
    歹
    0.47
    ۔
    0.44
    邡
    0.43
    ።
    0.43
     موض
    0.42
     મારા
    0.42
    HttpSession
    0.42
     Coldplay
    0.41
    。
    0.41
     nhạc
    0.41
    Activations Density 0.000%

    No Known Activations