© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 108481
    Prev
    Next
    INDEX
    Explanations

    file headers and comments

    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
    Arun
    -0.71
     Arun
    -0.67
    镕
    -0.66
    ཻ
    -0.66
    estors
    -0.65
     Jop
    -0.65
     misled
    -0.64
     Bulletin
    -0.64
    SCP
    -0.63
     Philo
    -0.63
    POSITIVE LOGITS
    awaiter
    0.73
     removable
    0.72
    描き
    0.71
     ژاپ
    0.70
     аргу
    0.69
     floating
    0.69
     bl
    0.69
     opposed
    0.68
    送り
    0.68
     commercially
    0.68
    Activations Density 0.053%

    No Known Activations