© 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. 17498
    Prev
    Next
    INDEX
    Explanations

    variable declarations and assignments

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

    variable assignment

    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
    мм
    0.52
    的
    0.49
    히
    0.48
    amsung
    0.46
    מק
    0.45
    ოტ
    0.44
    hdd
    0.44
    spinlock
    0.44
    С
    0.44
    text
    0.44
    POSITIVE LOGITS
     `=
    0.46
    ^{*}=
    0.46
     Ärz
    0.42
     enseñar
    0.42
    ?’
    0.41
     Instrumentation
    0.40
     Mustache
    0.40
     Liberals
    0.40
     onboard
    0.40
     =
    0.39
    Activations Density 0.000%

    No Known Activations