Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 9-GEMMASCOPE-2-RES-262K
    4. 7357
    Prev
    Next
    INDEX
    Explanations

    return app, every person

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_9_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
     TIMESTAMP
    1.29
     회
    1.28
     spermat
    1.27
     cytotoxicity
    1.25
     repay
    1.23
     Hebrews
    1.22
    də
    1.22
     diversifying
    1.22
     reactance
    1.21
    ితే
    1.21
    POSITIVE LOGITS
    er
    1.22
    n
    1.18
    hea
    1.08
    тап
    1.07
    izarea
    1.05
     restric
    1.04
    pl
    1.02
    ikes
    1.02
    inar
    1.02
     cual
    1.01
    Activations Density 0.000%

    No Known Activations