© 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. 66153
    Prev
    Next
    INDEX
    Explanations

    talking with someone

    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
    牁
    -2.31
    鈊
    -2.16
     ขนาด
    -2.06
    𓐍
    -1.98
     manchen
    -1.92
     kurzem
    -1.89
    闓
    -1.88
     welchem
    -1.85
    ↵
    -1.84
    といって
    -1.83
    POSITIVE LOGITS
    \
    2.61
     and
    1.97
     unſ
    1.91
    沩
    1.80
    C
    1.78
     initWithFrame
    1.77
    #\
    1.73
    ⃗
    1.73
    踽
    1.71
    \%
    1.70
    Activations Density 0.008%

    No Known Activations