© 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. 123643
    Prev
    Next
    INDEX
    Explanations

    document titles/headings

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

    colons in metadata headers or structured document formatting.

    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
    Ṇ
    -1.38
    ítulos
    -1.33
     የ
    -1.33
    ﮏ
    -1.33
    EClass
    -1.31
     millioner
    -1.30
    蓠
    -1.30
    ⚋
    -1.28
     ortodo
    -1.28
    örungen
    -1.28
    POSITIVE LOGITS
     Hinsicht
    1.64
     the
    1.52
    两
    1.49
    ました
    1.48
     about
    1.48
     almeno
    1.47
    Colabor
    1.46
    很难
    1.45
    Karakteristik
    1.45
    attenzione
    1.44
    Activations Density 0.015%

    No Known Activations