© 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-3-4B-IT
    3. 17-GEMMASCOPE-2-RES-16K
    4. 9191
    Prev
    Next
    INDEX
    Explanations

    subtlety and abstract concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-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
    了一个
    0.74
    ните
    0.70
     cytotoxic
    0.67
    颗
    0.66
    Fortunately
    0.65
    тный
    0.63
     unul
    0.63
    ется
    0.62
    Medic
    0.61
    Ordinate
    0.61
    POSITIVE LOGITS
    t
    0.91
    en
    0.91
    tss
    0.74
    tad
    0.73
    tä
    0.69
    ੀ
    0.66
    h
    0.65
    thed
    0.64
    tia
    0.63
     complexities
    0.62
    Activations Density 0.028%

    No Known Activations