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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 10035
    Prev
    Next
    INDEX
    Explanations

    goal is to

    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
     Aufenthal
    -1.70
    寕
    -1.68
     pegatinas
    -1.61
    ところが
    -1.58
    </td>
    -1.57
    馋
    -1.56
    "))
    -1.54
    ristiana
    -1.51
    新潟
    -1.49
    Ἢ
    -1.49
    POSITIVE LOGITS
    al
    2.13
    ar
    1.87
    so
    1.81
    骉
    1.68
     continuer
    1.65
    an
    1.64
    os
    1.62
    go
    1.59
    son
    1.53
    穑
    1.49
    Activations Density 0.038%

    No Known Activations