© 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. 34-GEMMASCOPE-RES-131K
    7. 78514
    Prev
    Next
    INDEX
    Explanations

    achievements or award titles

    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
    :{},
    -0.76
     daripada
    -0.75
    cnt
    -0.75
     mahu
    -0.74
     impossible
    -0.70
    块钱
    -0.69
     gela
    -0.68
     diye
    -0.66
    CNT
    -0.65
    Propor
    -0.65
    POSITIVE LOGITS
    ở
    0.84
    ĩa
    0.83
    ̞
    0.77
    newBuilder
    0.76
    iltà
    0.75
     кө
    0.74
    treasure
    0.73
     shipbuilding
    0.72
     widows
    0.71
    fuente
    0.71
    Activations Density 0.018%

    No Known Activations