© 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. 10-GEMMASCOPE-RES-131K
    4. 70521
    Prev
    Next
    INDEX
    Explanations

    battery

    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
    he
    -1.31
    5
    -1.30
    ahren
    -1.23
    0
    -1.20
    hibited
    -1.20
    ės
    -1.19
    {}'.
    -1.19
    7
    -1.18
     cabelos
    -1.18
     ,
    -1.16
    POSITIVE LOGITS
    バッテリー
    1.23
     signify
    1.20
     informé
    1.17
    teborg
    1.16
    データ
    1.14
     informée
    1.14
     они
    1.10
    ーム
    1.09
    ARON
    1.09
     detenidos
    1.08
    Activations Density 0.049%

    No Known Activations