© 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. 1973
    Prev
    Next
    INDEX
    Explanations

    numbers followed by punctuation

    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
    0.75
     ra
    0.69
     (
    0.64
     actual
    0.61
     att
    0.60
     gitt
    0.58
    rece
    0.58
     deb
    0.58
     je
    0.57
     /
    0.57
    POSITIVE LOGITS
    Aside
    0.93
     सऊदी
    0.89
    Remote
    0.88
    Buddhist
    0.88
    yLint
    0.86
     CHAN
    0.85
    棌
    0.85
    吘
    0.85
    Governance
    0.85
    㝡
    0.85
    Activations Density 0.255%

    No Known Activations