© 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. 110756
    Prev
    Next
    INDEX
    Explanations

    making, customised, important, secret

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

    being particularly, for a, with Under

    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
    t
    0.57
    S
    0.54
     האל
    0.54
     карто
    0.51
     стро
    0.49
    ланд
    0.48
    color
    0.48
     жени
    0.47
     прода
    0.46
    c
    0.45
    POSITIVE LOGITS
    泮
    0.52
     adhesives
    0.46
    ować
    0.44
    igsaw
    0.43
    гія
    0.43
    ढ़ा
    0.43
    ási
    0.43
    aties
    0.42
    atasi
    0.42
    ához
    0.42
    Activations Density 0.001%

    No Known Activations