© 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. 855
    Prev
    Next
    INDEX
    Explanations

    speech attribution

    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
    異なる
    0.79
    तया
    0.77
    Through
    0.77
    verted
    0.76
    Media
    0.76
    CaCl
    0.76
     발생
    0.73
    ᆹ
    0.73
    idx
    0.73
    Allium
    0.72
    POSITIVE LOGITS
     said
    0.89
    said
    0.85
     ujar
    0.83
     explicó
    0.82
    utica
    0.82
     chair
    0.81
     says
    0.80
     explained
    0.80
     replied
    0.79
     exclaimed
    0.79
    Activations Density 0.026%

    No Known Activations