© 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. 30649
    Prev
    Next
    INDEX
    Explanations

    information and status

    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
     publicó
    -0.85
    uſ
    -0.85
    hael
    -0.85
    etzal
    -0.85
    зд
    -0.83
    cesi
    -0.82
     deberán
    -0.82
    ób
    -0.82
    licability
    -0.82
    CCC
    -0.82
    POSITIVE LOGITS
     status
    1.67
     information
    1.61
     current
    1.40
    Status
    1.31
    status
    1.27
     Status
    1.22
    current
    1.19
     STATUS
    1.13
     статус
    1.11
     info
    1.09
    Activations Density 0.041%

    No Known Activations