© 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. 50005
    Prev
    Next
    INDEX
    Explanations

    begins, major, transaction

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

    generating labels, needed downtime, necessary action, affordable subscription

    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
     Bork
    0.50
     LongNumber
    0.48
    আন
    0.47
    ]/
    0.46
    )]:
    0.45
    ujące
    0.44
    ♢
    0.44
    蘇
    0.44
     on
    0.43
     Kear
    0.43
    POSITIVE LOGITS
    o
    0.57
    $(\
    0.50
    emis
    0.46
    epar
    0.46
    ilim
    0.44
    il
    0.44
    dependence
    0.44
    iliency
    0.44
    loom
    0.43
    dropped
    0.43
    Activations Density 0.000%

    No Known Activations