© 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-16K
    7. 1375
    Prev
    Next
    INDEX
    Explanations

    code keywords and symbols

    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_16k_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
     και
    1.55
     અને
    1.53
     데이터
    1.42
     וה
    1.40
     và
    1.37
     และ
    1.36
     및
    1.30
     ಮತ್ತು
    1.30
     Và
    1.30
    하고
    1.30
    POSITIVE LOGITS
    enf
    0.83
     prohibitive
    0.75
    makers
    0.75
    clothes
    0.72
    阴
    0.72
    感
    0.71
     distractions
    0.71
     mature
    0.71
    mature
    0.71
     dich
    0.71
    Activations Density 0.000%

    No Known Activations