© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 10754
    Prev
    Next
    INDEX
    Explanations

    like or style descriptors

    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_22_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
    សិក
    0.71
    гора
    0.70
     Ed
    0.67
    टेन
    0.67
     וה
    0.66
     Intelligent
    0.66
    ଥ
    0.66
    <unused2110>
    0.65
    ónimo
    0.65
     Word
    0.64
    POSITIVE LOGITS
     style
    2.57
    style
    2.54
    般的
    2.15
    esque
    2.12
    Style
    2.12
     Style
    2.06
    风格
    2.04
     estilo
    2.04
    like
    1.98
    achtige
    1.98
    Activations Density 0.360%

    No Known Activations