© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 67680
    Prev
    Next
    INDEX
    Explanations

    breakage and breaking

    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
     нового
    -1.93
    珢
    -1.88
     theses
    -1.83
    </h3>
    -1.77
    .
    -1.73
    0
    -1.68
     Their
    -1.66
     answers
    -1.64
     των
    -1.64
    老者
    -1.63
    POSITIVE LOGITS
    </b>
    1.84
     словно
    1.70
    ‘
    1.66
     juiste
    1.66
    end
    1.64
     WaitForSeconds
    1.63
    ŚĆ
    1.62
    娱乐圈
    1.59
     España
    1.56
    StoryboardSegue
    1.55
    Activations Density 0.019%

    No Known Activations