© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 32128
    Prev
    Next
    INDEX
    Explanations

    code comments and commands

    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
    WORTH
    -0.76
     Jude
    -0.76
     pregi
    -0.76
    Judge
    -0.75
    曖昧さ回避
    -0.75
     utilidad
    -0.74
     treaty
    -0.73
     bale
    -0.73
    satunya
    -0.73
     них
    -0.72
    POSITIVE LOGITS
    TryGetValue
    0.74
    CreateUser
    0.72
    MFC
    0.71
     maximise
    0.70
    最大
    0.69
    《
    0.67
     Defective
    0.66
     maximize
    0.65
    max
    0.65
     max
    0.64
    Activations Density 0.008%

    No Known Activations