© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 19875
    Prev
    Next
    INDEX
    Explanations

    code definitions involving "int"

    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
    ﺯ
    0.47
    ﯽ
    0.47
    @]
    0.46
     tendrás
    0.45
     wirst
    0.44
    キロ
    0.43
     фраг
    0.43
     अनुरोध
    0.43
     নাকের
    0.43
    意
    0.43
    POSITIVE LOGITS
    жах
    0.45
     laboratories
    0.44
     Palisades
    0.43
     economically
    0.42
     LaSalle
    0.42
     classifying
    0.41
     deriva
    0.41
    ValMap
    0.40
     masas
    0.40
     Kval
    0.39
    Activations Density 0.003%

    No Known Activations