© 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. 14658
    Prev
    Next
    INDEX
    Explanations

    multiple choice options

    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
     AutoCAD
    0.93
     മത
    0.87
     ::
    0.85
     Tetr
    0.84
     serm
    0.84
     gastronomy
    0.84
     zählt
    0.84
     SSL
    0.84
     Pokemon
    0.83
     zost
    0.83
    POSITIVE LOGITS
    или
    1.03
    З
    0.87
    hundred
    0.86
    หรือ
    0.82
     ప్రకారం
    0.81
    tested
    0.79
    morning
    0.79
     или
    0.78
    instead
    0.78
    suggest
    0.78
    Activations Density 0.077%

    No Known Activations