© 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. 34-GEMMASCOPE-RES-131K
    7. 93928
    Prev
    Next
    INDEX
    Explanations

    followed by 'out' or 'outs'

    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_34/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
    สำ
    -0.72
    kq
    -0.71
     Masses
    -0.69
     gof
    -0.69
     Fs
    -0.68
     Bordeaux
    -0.68
    ullen
    -0.67
    AMOR
    -0.67
     كلمة
    -0.67
     Behör
    -0.66
    POSITIVE LOGITS
    outs
    3.22
     outs
    3.13
    out
    3.08
     Outs
    2.20
    OUT
    2.08
    Out
    2.06
    Outs
    1.98
     Out
    1.95
    アウト
    1.93
     OUT
    1.84
    Activations Density 0.057%

    No Known Activations