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-3-1B
    3. 13-GEMMASCOPE-2-RES-16K
    4. 3948
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    鹉
    1.76
    writerow
    1.63
    ר
    1.59
     تعالی
    1.57
    تقاوى
    1.56
    rocess
    1.56
    ҽ
    1.53
    spike
    1.47
    ్రే
    1.47
    tree
    1.45
    POSITIVE LOGITS
    ..");
    1.50
    superuser
    1.46
    ٰی
    1.44
     overarching
    1.42
     shortened
    1.41
    ્યાં
    1.37
     jednotliv
    1.37
    }+(\
    1.37
     borrowed
    1.37
    চনার
    1.37
    Activations Density 0.000%

    No Known Activations