© 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. 7076
    Prev
    Next
    INDEX
    Explanations

    operational workflows

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

    identifying official context method deviations

    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
    0
    0.48
    C
    0.43
    b
    0.42
    2
    0.42
    K
    0.42
    W
    0.41
    i
    0.40
    R
    0.40
    B
    0.39
    A
    0.39
    POSITIVE LOGITS
     そんな
    0.37
     datth
    0.36
     angustato
    0.34
     returnMe
    0.34
    ргә
    0.34
    🚵
    0.34
    fireFlower
    0.33
     của
    0.33
    ጋገብ
    0.33
    echolog
    0.32
    Activations Density 0.877%

    No Known Activations