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. 8760
    Prev
    Next
    INDEX
    Explanations

    OpenSSL::Engine

    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
     Halliday
    -0.82
    pica
    -0.79
    Nirvana
    -0.72
    tieg
    -0.71
     watershed
    -0.71
     ſame
    -0.71
     Gog
    -0.70
     glider
    -0.70
    থা
    -0.69
    ミナル
    -0.69
    POSITIVE LOGITS
    ۔
    0.84
     ctx
    0.83
    Inform
    0.80
     ساخت
    0.79
    inform
    0.78
    CTX
    0.77
     STACK
    0.76
    amethasone
    0.76
    昆
    0.75
    icioso
    0.73
    Activations Density 0.042%

    No Known Activations