© 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. 57261
    Prev
    Next
    INDEX
    Explanations

    confronted by

    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
     aceea
    -0.68
    ผลิต
    -0.68
    Dorothy
    -0.67
    菩
    -0.67
    Podcast
    -0.66
    orah
    -0.65
    .='
    -0.65
    Rox
    -0.64
    inputFile
    -0.64
     CEN
    -0.64
    POSITIVE LOGITS
    ZZA
    0.80
     target
    0.74
    issus
    0.70
     ampla
    0.67
    piper
    0.67
     Wieder
    0.66
    utant
    0.65
     Side
    0.65
     πάντα
    0.65
    Side
    0.64
    Activations Density 0.053%

    No Known Activations