© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 118480
    Prev
    Next
    INDEX
    Explanations

    source code and licensing

    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
    Quota
    -0.73
    Cock
    -0.72
    Translatef
    -0.69
    Amm
    -0.67
     abreast
    -0.66
    diffic
    -0.66
     podí
    -0.66
    医药
    -0.66
    žité
    -0.66
    ielded
    -0.66
    POSITIVE LOGITS
    bpm
    0.75
    tier
    0.71
    lue
    0.71
    戸
    0.69
    enziale
    0.69
    oui
    0.69
    ществует
    0.69
     USER
    0.68
    alias
    0.68
     diperlukan
    0.66
    Activations Density 0.057%

    No Known Activations