© 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. 123581
    Prev
    Next
    INDEX
    Explanations

    textual headers and specific entities

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

    line breaks in LaTeX code or formatted text (specifically the `\\` line break command).

    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
     But
    -2.56
     メニュー
    -2.23
    却又
    -2.19
    辚
    -2.05
    ൎ
    -1.99
     вси
    -1.99
    鉝
    -1.95
    恼
    -1.94
    вании
    -1.92
     จาก
    -1.91
    POSITIVE LOGITS
     самых
    2.48
    i
    2.31
    re
    2.30
    to
    2.27
    their
    2.25
    ра
    2.23
    h
    2.22
    and
    2.13
    不愧
    2.08
    te
    2.06
    Activations Density 0.000%

    No Known Activations