© 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. 86588
    Prev
    Next
    INDEX
    Explanations

    German adjective and context

    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
    鹋
    -3.00
    </strong>
    -2.81
    瑒
    -2.48
     So
    -2.25
     essa
    -2.23
     was
    -2.23
     puertos
    -2.22
    t
    -2.22
    ￬
    -2.16
     monstruos
    -2.14
    POSITIVE LOGITS
    </td>
    2.61
    缫
    2.42
     レスト
    2.36
     crudo
    2.31
    0
    2.25
     tinto
    2.23
     チラシ
    2.22
    ֢
    2.22
     leone
    2.22
     tiveram
    2.20
    Activations Density 0.002%

    No Known Activations