© 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. 22-GEMMASCOPE-2-RES-16K
    7. 662
    Prev
    Next
    INDEX
    Explanations

    years

    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_22_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
    berat
    0.53
     endet
    0.53
     deste
    0.53
    mm
    0.52
    tm
    0.51
    㬶
    0.51
     мм
    0.51
     устро
    0.51
     этого
    0.49
    tay
    0.49
    POSITIVE LOGITS
    
    0.79
     ২০১২
    0.73
     راجسټ
    0.72
     ২০১০
    0.72
     Ebola
    0.71
     crowdfunding
    0.69
    Соцмережа
    0.68
     aDict
    0.68
    iophorus
    0.68
     ২০১৭
    0.67
    Activations Density 0.105%

    No Known Activations