© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 35289
    Prev
    Next
    INDEX
    Explanations

    web file paths

    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
     on
    -1.67
     for
    -1.47
     like
    -1.44
     from
    -1.44
     this
    -1.38
    ₆
    -1.18
    }));
    -1.17
     their
    -1.16
     even
    -1.14
    เดือน
    -1.14
    POSITIVE LOGITS
    دانلود
    1.35
    窺
    1.30
    raltar
    1.26
    بسم
    1.24
     rams
    1.20
    Ingredi
    1.20
    Sasuke
    1.18
    bilden
    1.18
    多彩
    1.17
    Frage
    1.16
    Activations Density 0.001%

    No Known Activations