© 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. 9355
    Prev
    Next
    INDEX
    Explanations

    odds ratios and confidence intervals

    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
     allgemeinen
    0.89
    堞
    0.87
     Handwritten
    0.87
     potter
    0.87
     దూర
    0.86
     asign
    0.86
    湎
    0.85
     सम्प
    0.85
     adot
    0.85
    Repartition
    0.84
    POSITIVE LOGITS
    range
    0.87
    truth
    0.85
    github
    0.80
    efficacy
    0.79
    ص
    0.79
    ل
    0.77
    jia
    0.75
    ج
    0.75
    PP
    0.74
    ర్లు
    0.74
    Activations Density 0.029%

    No Known Activations