© 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. 67773
    Prev
    Next
    INDEX
    Explanations

    can't seem to

    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
     is
    -1.55
     湾
    -1.52
    ೦
    -1.52
    筚
    -1.46
     kadın
    -1.44
     税
    -1.44
     when
    -1.42
    هو
    -1.41
    Ｂ
    -1.39
     Espanha
    -1.38
    POSITIVE LOGITS
    ‘
    1.94
     ‘
    1.74
    ’
    1.70
    なども
    1.69
     bezw
    1.63
    өз
    1.62
      
    1.61
    仿佛
    1.60
     wodurch
    1.57
     soprattutto
    1.53
    Activations Density 0.023%

    No Known Activations