© 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. 441
    Prev
    Next
    INDEX
    Explanations

    math expressions in tags

    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
    ,
    0.96
     check
    0.74
     (
    0.73
     to
    0.70
      
    0.65
     non
    0.61
     un
    0.60
     booming
    0.59
     inhib
    0.59
     mis
    0.58
    POSITIVE LOGITS
     chiede
    1.15
    十柒章
    1.12
     Ако
    1.10
    Một
    1.10
     jedan
    1.09
     frå
    1.09
    𒉌
    1.08
     Сьогодні
    1.08
     定义
    1.08
    ineuse
    1.07
    Activations Density 2.117%

    No Known Activations