© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 110528
    Prev
    Next
    INDEX
    Explanations

    user input and controls

    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
    словия
    -0.78
    ︿
    -0.77
    úmer
    -0.75
     flé
    -0.75
    送到
    -0.69
     законо
    -0.69
    ercises
    -0.68
     montant
    -0.67
    atoto
    -0.67
    立体
    -0.66
    POSITIVE LOGITS
     input
    4.47
     inputs
    4.00
     Input
    4.00
    input
    3.88
    Input
    3.88
     Inputs
    3.45
    inputs
    3.39
    INPUT
    3.27
    Inputs
    3.19
     INPUT
    3.16
    Activations Density 0.044%

    No Known Activations