© 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. 79958
    Prev
    Next
    INDEX
    Explanations

    Seller, submitted, father, Dr

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

    objective function, simple, FPS, pre-Socratics

    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
    중
    0.57
     excruciating
    0.51
    сії
    0.50
    쇤
    0.50
     السيارات
    0.50
     السيارة
    0.50
    elés
    0.47
     než
    0.47
    셍
    0.47
    要求的
    0.47
    POSITIVE LOGITS
    tone
    0.54
    time
    0.53
    fb
    0.52
    transformation
    0.49
     Transformation
    0.49
    tb
    0.49
    control
    0.49
    pdf
    0.48
    m
    0.48
    cosmos
    0.48
    Activations Density 0.000%

    No Known Activations