© 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
    2. Gemma-3-1B-IT
    3. 13-GEMMASCOPE-2-RES-16K
    4. 408
    Prev
    Next
    INDEX
    Explanations

    dialogue sentence endings

    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
     ویژه
    0.85
    !',
    0.76
    !).
    0.74
    체의
    0.74
    !".
    0.74
    :',
    0.73
     高級
    0.72
     phép
    0.72
    !",
    0.71
     꼭
    0.70
    POSITIVE LOGITS
     They
    0.99
     Referring
    0.85
    ,“
    0.84
    They
    0.82
     Asked
    0.80
     Were
    0.80
     Revenue
    0.79
     unloading
    0.79
     eyeing
    0.79
     With
    0.78
    Activations Density 0.112%

    No Known Activations