© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 85521
    Prev
    Next
    INDEX
    Explanations

    existence and its questions

    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
    镦
    -3.45
    甞
    -3.08
    s
    -3.08
    栳
    -2.81
    How
    -2.70
    筇
    -2.67
    蛲
    -2.63
    蟶
    -2.63
    When
    -2.53
    Could
    -2.39
    POSITIVE LOGITS
    ↵
    4.16
     of
    3.63
    ญี่ป
    3.28
    趼
    3.14
    
    3.09
     บาง
    2.80
     neuen
    2.69
    杳
    2.61
    䊐
    2.59
    
    2.55
    Activations Density 0.004%

    No Known Activations