© 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. 3180
    Prev
    Next
    INDEX
    Explanations

    the most important

    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
     oldukça
    0.69
     quite
    0.68
     \\\
    0.66
    леко
    0.66
    濘
    0.64
    acionales
    0.64
     typical
    0.62
    ikiem
    0.62
    лно
    0.62
     vives
    0.61
    POSITIVE LOGITS
    cannot
    0.74
    talent
    0.73
    Contrary
    0.72
     bond
    0.71
     talent
    0.69
    的第一
    0.68
     Bond
    0.67
    敵
    0.67
    bonus
    0.67
    聪
    0.67
    Activations Density 0.209%

    No Known Activations