© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 22686
    Prev
    Next
    INDEX
    Explanations

    modules and code constructs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     --
    0.41
     filters
    0.39
    typed
    0.39
     typed
    0.39
     distributes
    0.38
    --
    0.38
     receives
    0.38
     accumulates
    0.38
     genotype
    0.37
     appreciates
    0.37
    POSITIVE LOGITS
     submodule
    0.47
     módulos
    0.46
     modules
    0.42
    模块
    0.42
     subsystem
    0.42
    那边
    0.42
    Module
    0.40
    ဦ
    0.39
     departamento
    0.39
     szól
    0.39
    Activations Density 0.015%

    No Known Activations