© 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-3-4B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 3153
    Prev
    Next
    INDEX
    Explanations

    values indicated by percent

    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
     Burgh
    0.85
     Bolts
    0.84
     Diameter
    0.83
     hurled
    0.83
    涌
    0.82
     costos
    0.81
     Telegraph
    0.81
     ይጠ
    0.81
     unaccompanied
    0.81
     Hurry
    0.80
    POSITIVE LOGITS
     percentage
    2.00
     percent
    1.94
    percentage
    1.81
     percentages
    1.78
    percent
    1.75
    \%
    1.69
    Percentage
    1.68
    percentages
    1.66
    %,
    1.65
     fraction
    1.64
    Activations Density 0.661%

    No Known Activations