© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 129405
    Prev
    Next
    INDEX
    Explanations

    religious beliefs

    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_22/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
    bảng
    -1.30
     инстру
    -1.26
     economic
    -1.21
    thiết
    -1.16
    計画
    -1.16
    RTSN
    -1.15
    签订
    -1.14
    囔
    -1.14
    ibilidade
    -1.13
    ()?;
    -1.12
    POSITIVE LOGITS
     всичко
    1.43
     بسیاری
    1.32
     کرت
    1.24
     повече
    1.21
     حتی
    1.17
     uye
    1.15
     czerwony
    1.14
     seuls
    1.13
     abonnement
    1.12
     съдържа
    1.12
    Activations Density 0.033%

    No Known Activations