© 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. 17-GEMMASCOPE-2-RES-16K
    7. 3637
    Prev
    Next
    INDEX
    Explanations

    program code explanations

    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_17_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
    izowane
    0.77
    Two
    0.76
    Scaled
    0.69
     米
    0.68
    ন্দ্ব
    0.68
     two
    0.68
    ENABLE
    0.67
    two
    0.66
    Information
    0.66
    俩
    0.66
    POSITIVE LOGITS
     habló
    0.75
     passar
    0.74
     esperando
    0.73
     comun
    0.73
     señaló
    0.72
     parlare
    0.71
     dijo
    0.69
     espera
    0.69
     comunicaciones
    0.68
     giochi
    0.67
    Activations Density 0.089%

    No Known Activations