© 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. 2639
    Prev
    Next
    INDEX
    Explanations

    foreign characters or medical/technical terms

    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
     powdered
    0.69
     moistened
    0.68
     인
    0.60
     поло
    0.60
     Absence
    0.59
     ய
    0.59
     l
    0.59
     There
    0.58
     для
    0.58
     دم
    0.58
    POSITIVE LOGITS
    larini
    0.70
     ziff
    0.69
    <0xB2>
    0.67
    reff
    0.66
    plaatst
    0.66
    čan
    0.65
     taraf
    0.65
    gevens
    0.64
    घटना
    0.64
     হুমায়
    0.64
    Activations Density 0.009%

    No Known Activations