© 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. 1339
    Prev
    Next
    INDEX
    Explanations

    subjects and alternatives

    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
    搾
    0.85
    Rourke
    0.84
     jakim
    0.83
    empty
    0.79
     Object
    0.78
     "
    0.78
     σχέ
    0.77
     un
    0.76
     бы
    0.76
    Object
    0.75
    POSITIVE LOGITS
     maupun
    1.27
     and
    1.16
     및
    1.16
    และ
    1.15
    <unused2127>
    1.06
     এবং
    1.03
     và
    1.03
     மற்றும்
    1.02
    或其他
    1.02
    및
    1.01
    Activations Density 1.595%

    No Known Activations