© 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. 39208
    Prev
    Next
    INDEX
    Explanations

    harmful incidents

    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_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
     сеть
    -1.27
     algorit
    -1.25
    你有
    -1.25
    5
    -1.22
     Wikimedijinoj
    -1.21
     hiz
    -1.20
     ارائه
    -1.17
    ilidades
    -1.17
    ковым
    -1.17
    🫡
    -1.16
    POSITIVE LOGITS
     from
    1.42
    ㈡
    1.38
    čaj
    1.33
    čenie
    1.30
    ことになる
    1.28
    之际
    1.28
     such
    1.27
     in
    1.27
    をつける
    1.26
    鹋
    1.26
    Activations Density 0.239%

    No Known Activations