© 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. 40847
    Prev
    Next
    INDEX
    Explanations

    no idea what

    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
    出了一
    -1.66
     mesmos
    -1.61
     tă
    -1.60
    と同じ
    -1.52
     trám
    -1.50
    ⑊
    -1.45
     mismos
    -1.44
     manquante
    -1.40
    on
    -1.38
     dì
    -1.36
    POSITIVE LOGITS
     but
    1.84
    }
    1.70
     what
    1.62
     this
    1.59
     Einfluß
    1.46
     how
    1.42
    aucun
    1.38
     or
    1.37
     Verlust
    1.35
     ......
    1.34
    Activations Density 0.020%

    No Known Activations