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. 7507
    Prev
    Next
    INDEX
    Explanations

    latex environments and commands

    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
    }%
    
    -0.93
    greens
    -0.88
    untut
    -0.85
    ան
    -0.82
    tvguide
    -0.82
    ზ
    -0.78
     Cold
    -0.77
     hitta
    -0.77
    ských
    -0.77
     }{@
    -0.77
    POSITIVE LOGITS
    Kenzie
    0.88
     dụ
    0.86
    環境
    0.86
    बि
    0.84
    はお
    0.83
    onymus
    0.83
    ozof
    0.82
    ギ
    0.82
    UEZ
    0.82
     miſ
    0.82
    Activations Density 0.007%

    No Known Activations