© 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. 10-GEMMASCOPE-RES-131K
    7. 101288
    Prev
    Next
    INDEX
    Explanations

    Congress and senators

    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
    .
    -1.58
    Already
    -1.37
     lumineux
    -1.36
     rigide
    -1.34
    ?
    -1.32
     zie
    -1.31
     -
    -1.28
    姽
    -1.27
     fabriqué
    -1.25
    憷
    -1.25
    POSITIVE LOGITS
    parently
    1.42
     like
    1.40
     inclusief
    1.37
     gedurende
    1.35
     ligeramente
    1.33
    ridescent
    1.30
     ontvangen
    1.27
     gezegd
    1.25
     bepaald
    1.25
     membentuk
    1.23
    Activations Density 0.074%

    No Known Activations