© 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. 190278
    Prev
    Next
    INDEX
    Explanations

    beach, HT, information, admitted, sufficient, popular

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

    promise gone wrong

    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
    比如說
    0.45
    ρίας
    0.44
    镞
    0.43
    运动员
    0.43
    zęd
    0.42
    ွင်း
    0.42
    력
    0.42
    总裁
    0.42
    IO
    0.41
    wounded
    0.41
    POSITIVE LOGITS
     😊
    0.53
     iff
    0.51
     😉
    0.51
     emas
    0.49
     errori
    0.48
    😊
    0.48
     errores
    0.48
     oggetti
    0.47
     RoHS
    0.47
     Pythagoras
    0.47
    Activations Density 0.001%

    No Known Activations