© 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. 242202
    Prev
    Next
    INDEX
    Explanations

    URLs with parameters

    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
    ла
    0.50
    га
    0.50
     experimento
    0.47
     withstood
    0.47
    茶
    0.46
     желе
    0.44
    它可以
    0.44
    وية
    0.43
    крови
    0.43
    ية
    0.43
    POSITIVE LOGITS
    h
    0.56
     เอก
    0.48
    zano
    0.48
    NHK
    0.47
    haut
    0.46
    (/^\
    0.46
    b
    0.45
    intrinsic
    0.45
    YAN
    0.44
    exceptional
    0.44
    Activations Density 0.002%

    No Known Activations