© 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-3-1B-IT
    5. 13-GEMMASCOPE-2-RES-16K
    7. 1931
    Prev
    Next
    INDEX
    Explanations

    start of model response

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_13_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
     juez
    0.87
     største
    0.85
    Ό
    0.83
     då
    0.81
     rearr
    0.80
     grootste
    0.80
     Pérez
    0.80
     fini
    0.79
     રંગ
    0.77
     sít
    0.77
    POSITIVE LOGITS
     tourism
    0.85
     Handbook
    0.82
     sponsorship
    0.78
     outlines
    0.78
     migratory
    0.77
    ramed
    0.76
    
    0.75
    cheng
    0.75
     Outlook
    0.74
     outreach
    0.73
    Activations Density 0.185%

    No Known Activations