© 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. 251861
    Prev
    Next
    INDEX
    Explanations

    pioneering steps and body

    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
     Algonquin
    0.49
     takich
    0.48
    阃
    0.47
    性を
    0.46
     Veränder
    0.46
     Severity
    0.46
    就没有
    0.45
     magnitud
    0.45
     Survey
    0.45
     высоким
    0.45
    POSITIVE LOGITS
    К
    0.54
    lu
    0.53
    goes
    0.53
    claim
    0.52
    Brian
    0.52
    kkue
    0.52
    body
    0.51
    Cabe
    0.51
    es
    0.50
    members
    0.50
    Activations Density 0.000%

    No Known Activations