© 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. 189682
    Prev
    Next
    INDEX
    Explanations

    new writing event

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

    numbers, tuples, lists

    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
    ква
    0.52
    к
    0.49
     уско
    0.49
    консу
    0.47
     configuring
    0.47
    нду
    0.47
     disturbance
    0.46
    дован
    0.46
     нова
    0.46
     млн
    0.46
    POSITIVE LOGITS
    ED
    0.52
     l
    0.52
    目
    0.50
    ES
    0.49
    soe
    0.49
    sous
    0.49
    1
    0.49
    %
    0.48
    I
    0.47
     to
    0.46
    Activations Density 0.000%

    No Known Activations