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. 8930
    Prev
    Next
    INDEX
    Explanations

    code comments and keywords

    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
    uoti
    -0.92
    Ứng
    -0.88
     pram
    -0.85
    嚀
    -0.82
    //-
    -0.82
    //'
    -0.82
     restante
    -0.81
    Erfahrung
    -0.81
    aktu
    -0.79
    weitere
    -0.79
    POSITIVE LOGITS
    認め
    0.98
    diksi
    0.92
     下着
    0.85
     estable
    0.85
    late
    0.83
    nargs
    0.81
    flip
    0.81
     about
    0.81
     here
    0.80
    fortunate
    0.80
    Activations Density 0.001%

    No Known Activations