© 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. 115051
    Prev
    Next
    INDEX
    Explanations

    symptoms tricky

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

    technical documentation and code

    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
    a
    0.64
    ه
    0.59
    an
    0.59
    jt
    0.54
    aw
    0.54
    yen
    0.53
    ght
    0.52
    blade
    0.52
    yse
    0.52
    ere
    0.52
    POSITIVE LOGITS
     Distributions
    0.55
    炡
    0.52
     produktów
    0.50
    蜿
    0.49
    ৌজের
    0.48
     Produkten
    0.47
     Filtering
    0.47
     serii
    0.46
    今天的
    0.46
    ラの
    0.46
    Activations Density 0.001%

    No Known Activations