© 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. 7829
    Prev
    Next
    INDEX
    Explanations

    timesheet, child id, pacman, cw_mon, integral part

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

    code parameters and values

    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
    哺乳
    0.22
     proteolytic
    0.18
    猕
    0.18
    PERATURE
    0.18
    OLYBD
    0.18
    瘧
    0.18
    VSLU
    0.18
     carbohyd
    0.17
     бактери
    0.17
     없어
    0.17
    POSITIVE LOGITS
     Base
    0.22
     Data
    0.21
     Context
    0.21
     Real
    0.20
     Media
    0.19
     Geo
    0.19
     Full
    0.19
     Bit
    0.19
     Venture
    0.18
     X
    0.18
    Activations Density 0.092%

    No Known Activations