© 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-3-1B-IT
    5. 13-GEMMASCOPE-2-RES-65K
    7. 327
    Prev
    Next
    INDEX
    Explanations

    list item marker `*`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_13_width_65k_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
     inputs
    1.01
    Inputs
    0.96
    st
    0.95
    inputs
    0.94
     facts
    0.89
    لمات
    0.84
     Inputs
    0.83
    말
    0.83
    白天
    0.82
    原則
    0.82
    POSITIVE LOGITS
    ddots
    1.42
    蚬
    1.41
     لأ
    1.37
    ῎
    1.37
    乂
    1.36
     อ
    1.35
    Без
    1.35
    <0xF3>
    1.35
     کاکروچ
    1.35
    鉭
    1.34
    Activations Density 0.356%

    No Known Activations