© 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. 109312
    Prev
    Next
    INDEX
    Explanations

    backyard garden

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

    console logging messages

    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
    э
    0.52
     jogador
    0.47
     મારા
    0.46
     اللاعب
    0.46
     defect
    0.45
    ě
    0.44
    我
    0.43
     player
    0.42
     नुक
    0.42
     vorbe
    0.42
    POSITIVE LOGITS
    룸
    0.45
     stating
    0.45
     හො
    0.45
     والدین
    0.44
     uncontrolled
    0.44
     ملک
    0.42
    unused
    0.42
     کت
    0.42
    quantitative
    0.41
     مرک
    0.40
    Activations Density 0.000%

    No Known Activations