© 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. 47555
    Prev
    Next
    INDEX
    Explanations

    Caesar and, Georgia and

    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
     signed
    -0.75
    monds
    -0.71
    鮒
    -0.69
     Tijuana
    -0.68
     keynote
    -0.67
     sesama
    -0.67
    EDU
    -0.66
     mistake
    -0.66
     mistakes
    -0.66
    SP
    -0.65
    POSITIVE LOGITS
     validators
    1.12
    Louisiana
    0.96
    validators
    0.93
    Submit
    0.86
     Adele
    0.83
    VING
    0.81
     Submit
    0.80
    Hidden
    0.80
     Louisiana
    0.79
    chtung
    0.79
    Activations Density 0.003%

    No Known Activations