© 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-3-4B-IT
    3. 29-GEMMASCOPE-2-RES-262K
    4. 149675
    Prev
    Next
    INDEX
    Explanations

    Cornell University

    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_29_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
     Pupils
    0.75
    届
    0.74
    शा
    0.74
    음
    0.71
    েজ
    0.67
    俞
    0.67
    ச்சு
    0.66
    guard
    0.66
    를
    0.65
     curvy
    0.65
    POSITIVE LOGITS
     Mariano
    0.96
    enni
    0.92
     diariamente
    0.87
    ^{+}$
    0.85
    什麼
    0.83
    ियों
    0.81
     бое
    0.81
    atives
    0.80
     Aeron
    0.79
    ског
    0.78
    Activations Density 0.000%

    No Known Activations