© 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. 22-GEMMASCOPE-RES-131K
    7. 104527
    Prev
    Next
    INDEX
    Explanations

    ions across

    np_acts-logits-general · gemini-2.5-flash-lite

    specific tokens within programming code or technical content.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     siè
    -1.21
     hyö
    -1.05
     myriad
    -1.05
     occuper
    -1.05
     extérieurs
    -1.05
     parlement
    -1.05
     emporter
    -1.05
     participer
    -1.02
     ennemi
    -1.00
     célè
    -1.00
    POSITIVE LOGITS
    aternal
    0.98
     and
    0.93
    ........
    0.92
     proved
    0.90
    Ẩ
    0.87
    cated
    0.85
    Lá
    0.84
     becomes
    0.83
     fisik
    0.82
     subsequently
    0.81
    Activations Density 0.091%

    No Known Activations