© 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. 5035
    Prev
    Next
    INDEX
    Explanations

    inside the

    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
    নেট
    0.82
    ме
    0.82
    ızı
    0.78
    팩
    0.76
    بت
    0.76
    Ꮤ
    0.75
    ꒪
    0.73
     отсутствие
    0.73
    pwm
    0.70
     сайте
    0.70
    POSITIVE LOGITS
     parentheses
    1.07
     the
    0.99
    e
    0.93
     وخ
    0.82
     negeri
    0.82
     quotes
    0.82
     Lle
    0.77
     brackets
    0.77
     purview
    0.75
     linings
    0.75
    Activations Density 0.042%

    No Known Activations