© 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. 63393
    Prev
    Next
    INDEX
    Explanations

    articles and objects

    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
    aronder
    -0.91
    URERS
    -0.80
    byshev
    -0.79
    ummy
    -0.79
    въ
    -0.77
    ølge
    -0.73
     музыку
    -0.73
     refrigerators
    -0.73
    efficient
    -0.71
    titi
    -0.71
    POSITIVE LOGITS
     tray
    1.31
     drink
    1.31
     phone
    1.27
     tablet
    1.27
     newspaper
    1.20
     newspapers
    1.17
     bottle
    1.16
     microphone
    1.16
     drinks
    1.14
     notebook
    1.13
    Activations Density 0.036%

    No Known Activations