Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 22-GEMMASCOPE-2-RES-16K
    4. 7604
    Prev
    Next
    INDEX
    Explanations

    colon and foreign characters

    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
    also
    1.37
       
    1.02
    other
    1.01
     also
    1.00
    }.
    0.97
     voila
    0.97
     също
    0.94
     également
    0.92
     voilà
    0.89
    மேலும்
    0.88
    POSITIVE LOGITS
    :\
    0.83
     Gleich
    0.82
    नियां
    0.81
    ánicas
    0.80
    nungen
    0.79
     哈
    0.78
    नियों
    0.78
     кін
    0.77
    ாதீர்கள்
    0.76
    นั้น
    0.76
    Activations Density 0.303%

    No Known Activations