© 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. 10-GEMMASCOPE-RES-131K
    7. 11612
    Prev
    Next
    INDEX
    Explanations

    names and code identifiers

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

    capital letters that begin proper nouns, especially names.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     on
    -1.78
    着一个
    -1.69
    了几
    -1.37
    -
    -1.36
    saying
    -1.33
    几分
    -1.32
     patate
    -1.31
     pantaloni
    -1.30
     in
    -1.29
    phòng
    -1.29
    POSITIVE LOGITS
    ekw
    1.48
    chê
    1.45
     orgánico
    1.41
    '];
    1.39
    capai
    1.38
     giebt
    1.38
     übri
    1.38
    "];
    1.38
    tvguidetime
    1.38
     preferencias
    1.35
    Activations Density 0.461%

    No Known Activations