© 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. 1444
    Prev
    Next
    INDEX
    Explanations

    product beginnings

    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
     general
    0.73
     knowledge
    0.62
     all
    0.61
    ↵
    0.60
     overall
    0.59
     however
    0.57
    !
    0.57
     surprise
    0.56
     fac
    0.56
    general
    0.54
    POSITIVE LOGITS
    𒆘
    1.19
     ஜீயஸின்
    1.19
     gahetabbam
    1.19
    hrattr
    1.18
     gacchatiti
    1.17
    加入参数向量中
    1.17
    𒂱
    1.17
    asaddassa
    1.17
    𒐻
    1.17
     加入层
    1.17
    Activations Density 0.048%

    No Known Activations