© 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. 105088
    Prev
    Next
    INDEX
    Explanations

    numbers and rounding directions

    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
    橚
    -3.16
    ᯾
    -2.69
    𖣔
    -2.66
    âneo
    -2.58
    1
    -2.56
    苤
    -2.56
    鳎
    -2.52
    
    -2.45
    鸸
    -2.45
    蟜
    -2.45
    POSITIVE LOGITS
     They
    3.20
    that
    3.09
    '
    2.88
    躥
    2.83
    </h1>
    2.47
     That
    2.42
     myſelf
    2.41
    啻
    2.33
    <i>
    2.30
    an
    2.30
    Activations Density 0.123%

    No Known Activations