© 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. 65774
    Prev
    Next
    INDEX
    Explanations

    dumpster waste management

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

    requires planning

    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
    endtime
    0.47
    lyan
    0.46
    検
    0.45
    އ
    0.45
    ناك
    0.45
    zeitig
    0.44
    <0x85>
    0.43
    raining
    0.43
    teenage
    0.42
    zeit
    0.42
    POSITIVE LOGITS
     PROGRESS
    0.44
     STRUCTURE
    0.44
    ULO
    0.44
    Ế
    0.43
     Slug
    0.43
     দিয়াছেন
    0.43
    PLA
    0.43
    στημα
    0.43
    σταση
    0.42
     Caught
    0.42
    Activations Density 0.009%

    No Known Activations