© 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. 15048
    Prev
    Next
    INDEX
    Explanations

    non-aggression

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

    DCT, noise, alloys, land

    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
     automóviles
    0.48
    órmula
    0.41
     automobiles
    0.41
     periódico
    0.39
     কথাই
    0.39
    ată
    0.39
     communément
    0.39
    鿌
    0.39
     Automobiles
    0.38
    ädt
    0.38
    POSITIVE LOGITS
     differentially
    0.47
     symmetric
    0.47
     proactively
    0.46
     redefining
    0.45
     overexpression
    0.45
     BETWEEN
    0.45
     between
    0.44
     webhook
    0.43
     countering
    0.43
     selectively
    0.42
    Activations Density 0.001%

    No Known Activations