© 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. 158701
    Prev
    Next
    INDEX
    Explanations

    without notice

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

    superlatives and descriptors

    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
     大き
    0.48
    navigationItem
    0.48
     мнение
    0.46
    릅
    0.45
    сё
    0.45
    (*(
    0.45
     勝
    0.45
    myTransform
    0.44
    ∑</
    0.44
    偉
    0.44
    POSITIVE LOGITS
     à
    0.56
     reçoit
    0.50
    oden
    0.49
     exclusives
    0.49
     connues
    0.49
     Brice
    0.48
     étudi
    0.48
     valide
    0.48
     sama
    0.47
     immun
    0.47
    Activations Density 0.001%

    No Known Activations