© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 48159
    Prev
    Next
    INDEX
    Explanations

    disable/disabled

    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
    繊細
    -1.14
    写真の
    -1.13
     beset
    -1.13
     inept
    -1.12
    癒し
    -1.12
    気持ちを
    -1.11
    かと思います
    -1.10
     unfailing
    -1.10
    Highlighted
    -1.09
     emprego
    -1.09
    POSITIVE LOGITS
    Unless
    1.23
    將
    1.20
    setDisable
    1.19
    For
    1.16
    我們
    1.16
     Desember
    1.15
    tling
    1.13
     disabled
    1.13
    Completely
    1.12
    ()!=
    1.11
    Activations Density 0.014%

    No Known Activations