© 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. 123715
    Prev
    Next
    INDEX
    Explanations

    frequency

    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
     haupts
    -2.48
    ).”
    -2.42
    .?
    -2.27
    ↵↵
    -2.22
    ?”
    -2.19
    ..?
    -2.16
    nessy
    -2.16
    .’
    -2.14
    秾
    -2.13
     vielleicht
    -2.11
    POSITIVE LOGITS
     ľudí
    2.36
     händer
    2.28
    猹
    2.27
    …！
    2.23
    yyy
    2.16
    趼
    2.13
    𓆸
    2.11
    ྅
    2.08
    /////
    2.06
    liğ
    2.06
    Activations Density 0.039%

    No Known Activations