© 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. 175929
    Prev
    Next
    INDEX
    Explanations

    numbers and quantities

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

    technical steps and instructions

    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
    t
    0.63
    thed
    0.49
    titor
    0.49
    tss
    0.47
     Experienced
    0.47
    V
    0.46
    tics
    0.46
     Academic
    0.45
    tdd
    0.45
     Ecole
    0.45
    POSITIVE LOGITS
     রহ
    0.49
    組み
    0.44
    산업
    0.44
    幹線
    0.44
    產業
    0.44
    に見
    0.44
     dignified
    0.44
     промышлен
    0.43
     যৌ
    0.43
    労
    0.43
    Activations Density 0.000%

    No Known Activations