© 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. 65569
    Prev
    Next
    INDEX
    Explanations

    surnames starting with Hod

    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
    }
    -3.11
     In
    -2.75
    龊
    -2.48
    的高
    -2.39
    which
    -2.38
    ."
    -2.36
    .…
    -2.33
    仉
    -2.20
    codiles
    -2.17
     curiously
    -2.16
    POSITIVE LOGITS
    genodigd
    2.59
    
    2.44
     aktuelle
    2.25
     ผม
    2.23
     fantástica
    2.22
    the
    2.13
    所以我
    2.08
    姽
    2.08
     Германия
    2.08
    arthed
    2.06
    Activations Density 0.003%

    No Known Activations