© 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. 35266
    Prev
    Next
    INDEX
    Explanations

    file paths and package names

    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
    having
    -1.45
    through
    -1.36
    それを
    -1.30
     dieselbe
    -1.26
    those
    -1.24
     vone
    -1.21
    his
    -1.20
     seinen
    -1.17
    ↵↵↵
    -1.17
     ihren
    -1.16
    POSITIVE LOGITS
     our
    1.54
     and
    1.48
     both
    1.38
     about
    1.23
     hermosos
    1.20
    の一覧
    1.18
    vät
    1.18
    Ӿ
    1.15
     Poets
    1.10
    我が家の
    1.10
    Activations Density 0.008%

    No Known Activations