© 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. 137923
    Prev
    Next
    INDEX
    Explanations

    happy, relationship, resource, set

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

    maximum security prison and unrest

    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
     contexte
    0.50
     ře
    0.49
     fête
    0.49
     forêt
    0.48
     plateforme
    0.47
    람
    0.47
    skou
    0.47
     본
    0.46
     resolute
    0.46
    साठी
    0.46
    POSITIVE LOGITS
    ATIONAL
    0.48
    EnglishMarks
    0.48
    бурга
    0.47
    িতাম
    0.46
    MUL
    0.46
    [,-
    0.45
    elcome
    0.43
     stickers
    0.42
    чи
    0.42
    >>(
    0.42
    Activations Density 0.000%

    No Known Activations