© 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. 2802
    Prev
    Next
    INDEX
    Explanations

    numbered lists with colons

    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
     tasks
    0.93
     choose
    0.90
     [
    0.90
     standard
    0.90
       
    0.90
     buttons
    0.89
     stored
    0.89
     create
    0.88
     make
    0.87
     configurable
    0.85
    POSITIVE LOGITS
    Transicao
    1.09
    癃
    1.04
    CharAt
    0.97
    ChangeString
    0.97
    PhCH
    0.96
    Acetoxy
    0.96
    čenja
    0.95
    ᠩ
    0.90
    弓
    0.89
    accar
    0.89
    Activations Density 0.174%

    No Known Activations