© 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. 77949
    Prev
    Next
    INDEX
    Explanations

    technical community posts

    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
     Website
    -0.93
     WEBSITE
    -0.87
    Hä
    -0.83
    Website
    -0.79
    kursi
    -0.74
    pria
    -0.73
    topRight
    -0.73
     '/';
    -0.72
    StatusOK
    -0.72
     Č
    -0.71
    POSITIVE LOGITS
     SCN
    1.05
     communities
    0.92
     SDN
    0.89
    Message
    0.88
     Consultants
    0.86
    SAP
    0.85
     gurus
    0.85
     consultants
    0.84
    communities
    0.84
    SCN
    0.81
    Activations Density 0.075%

    No Known Activations