© 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. 57423
    Prev
    Next
    INDEX
    Explanations

    Corbin, Corretti, Corman

    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
    Cognitive
    -0.78
    sorting
    -0.76
     Cognitive
    -0.76
    STT
    -0.75
    قليم
    -0.75
    歉
    -0.75
     operas
    -0.74
     Keeping
    -0.74
    認為
    -0.70
     asci
    -0.69
    POSITIVE LOGITS
    Cor
    1.16
    cor
    1.02
    COR
    1.02
     Cor
    1.02
     cor
    0.98
     vanlig
    0.98
     COR
    0.92
     Кор
    0.86
    ⵣ
    0.79
    Кор
    0.79
    Activations Density 0.072%

    No Known Activations