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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 48673
    Prev
    Next
    INDEX
    Explanations

    topic titles

    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
     proudly
    -0.94
    siyah
    -0.88
    anyon
    -0.85
    fangs
    -0.84
    孫
    -0.84
     ASSETS
    -0.82
    Serve
    -0.81
    odyne
    -0.79
     Vorte
    -0.79
    IPMENT
    -0.79
    POSITIVE LOGITS
    tissage
    0.78
    andowski
    0.73
     đeo
    0.69
    зывали
    0.69
    dub
    0.67
     zůst
    0.67
     остался
    0.66
    Spi
    0.66
     развер
    0.66
     rodeado
    0.65
    Activations Density 0.000%

    No Known Activations