© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 118895
    Prev
    Next
    INDEX
    Explanations

    index and percent

    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
    $\$
    -1.06
    booted
    -0.81
    複数の
    -0.81
    ){$\
    -0.77
    这种
    -0.73
    含ま
    -0.72
    oxone
    -0.71
    toes
    -0.71
    PageFactory
    -0.71
    flop
    -0.71
    POSITIVE LOGITS
     points
    1.23
     index
    0.90
     punten
    0.89
     Punkten
    0.87
     Points
    0.85
     CFD
    0.82
     its
    0.82
    七夕
    0.82
     légèrement
    0.82
    points
    0.81
    Activations Density 0.010%

    No Known Activations