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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 90010
    Prev
    Next
    INDEX
    Explanations

    responses and comments

    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
    ciech
    -0.81
    Riding
    -0.75
    czka
    -0.75
    čina
    -0.74
    arusian
    -0.73
    cosa
    -0.72
    ulsar
    -0.72
    voegen
    -0.71
    告诉我
    -0.71
     CONCEPTS
    -0.71
    POSITIVE LOGITS
     responses
    1.82
     response
    1.78
     Responses
    1.63
     replies
    1.54
     respond
    1.51
     responds
    1.47
     reply
    1.42
    responses
    1.41
    response
    1.39
     responded
    1.38
    Activations Density 0.020%

    No Known Activations