© 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. 12397
    Prev
    Next
    INDEX
    Explanations

    `$` followed by common code identifiers or punctuation

    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
    ”;
    -2.36
    a
    -2.30
     некоторые
    -2.19
    if
    -2.17
    ”,
    -2.16
     But
    -2.11
     penchant
    -2.05
     kleinen
    -2.05
     なし
    -1.97
    र
    -1.94
    POSITIVE LOGITS
    伱
    2.33
    autogui
    2.33
     упаковке
    2.27
    为啥
    2.25
    眎
    2.22
    .$
    2.19
    ‪.‬‬
    2.17
    倅
    2.03
    娓
    2.03
     ונ
    2.02
    Activations Density 0.001%

    No Known Activations