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-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 8647
    Prev
    Next
    INDEX
    Explanations

    printf format specifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    主意
    -0.91
     cesto
    -0.82
     Pearce
    -0.77
     Lewiston
    -0.75
    دانشنامهٔ
    -0.74
     cumpli
    -0.74
    辘
    -0.73
    fions
    -0.73
     cantora
    -0.71
    ͤ
    -0.71
    POSITIVE LOGITS
    Pře
    0.90
    ``,
    0.84
    となりました
    0.83
    ''',
    0.82
     [],
    0.82
    켰
    0.79
    pointer
    0.79
    sequently
    0.77
     Rahman
    0.77
    \
    0.77
    Activations Density 0.007%

    No Known Activations