© 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
    3. Gemma-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-262K
    7. 7357
    Prev
    Next
    INDEX
    Explanations

    social science journals

    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_22_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
     cytotoxicity
    1.20
     repay
    1.20
     spermat
    1.18
     diversifying
    1.16
     회
    1.15
     allevi
    1.14
     Hebrews
    1.13
    ◁
    1.11
     REP
    1.10
    ితే
    1.10
    POSITIVE LOGITS
     restric
    1.00
    n
    0.99
    тап
    0.99
    er
    0.98
     cual
    0.92
    uksi
    0.91
    hea
    0.91
    ear
    0.90
    года
    0.88
     sende
    0.88
    Activations Density 0.000%

    No Known Activations