© 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. 100483
    Prev
    Next
    INDEX
    Explanations

    constant DISABLE

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

    defining programming constants

    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
    ሳሌ
    0.48
    檛
    0.47
    மன
    0.46
     اتارنا
    0.46
     кілька
    0.45
     ನ್ಯಾಯ
    0.44
     બનાવી
    0.44
    ocsát
    0.43
    बॉल
    0.42
    𒁲
    0.42
    POSITIVE LOGITS
    =
    0.49
     delic
    0.47
     minerals
    0.45
     constants
    0.45
     concepts
    0.45
     rectangular
    0.44
     trunc
    0.44
     marks
    0.44
    concepts
    0.44
     rom
    0.43
    Activations Density 0.000%

    No Known Activations