© 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. 128073
    Prev
    Next
    INDEX
    Explanations

    what something concerns

    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
    製の
    -1.59
     Krieges
    -1.54
    幛
    -1.52
    的在
    -1.43
     colombiana
    -1.40
    —"
    -1.39
     distanci
    -1.38
     such
    -1.37
     dava
    -1.34
    '
    -1.34
    POSITIVE LOGITS
     is
    1.80
    s
    1.62
    Otra
    1.53
     }
    1.49
    いぐるみ
    1.48
     entirety
    1.46
     einheit
    1.43
     $
    1.43
    at
    1.40
    uſe
    1.38
    Activations Density 0.049%

    No Known Activations