© 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. 43868
    Prev
    Next
    INDEX
    Explanations

    js build tools

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

    task and target names

    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
     traceback
    0.43
    窗
    0.41
    usermodel
    0.41
     দ্বিতীয়
    0.41
    𝐠
    0.40
    шымта
    0.40
    oj
    0.40
     Console
    0.40
     SW
    0.39
     thermocouple
    0.39
    POSITIVE LOGITS
    registerTask
    0.54
     palab
    0.45
    طة
    0.45
     evanes
    0.44
     unproductive
    0.44
    🖕
    0.43
     cher
    0.43
     🙌
    0.42
     anga
    0.42
    🧚
    0.42
    Activations Density 0.000%

    No Known Activations