© 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. 228458
    Prev
    Next
    INDEX
    Explanations

    John, Christ's apostles, Him

    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
    thinking
    0.51
    Is
    0.50
    vo
    0.48
    collide
    0.48
    VO
    0.48
    food
    0.48
    伍章
    0.48
    අ
    0.47
    os
    0.47
    removing
    0.47
    POSITIVE LOGITS
     verbally
    0.53
     thirties
    0.53
     refinancing
    0.50
     Saturday
    0.48
     magnifying
    0.48
     hypothetical
    0.48
     ноутбу
    0.47
     вчера
    0.47
     yesterday
    0.46
     postpaid
    0.46
    Activations Density 0.001%

    No Known Activations