© 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. 59518
    Prev
    Next
    INDEX
    Explanations

    Alexandria Ariana

    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
     their
    -1.06
    ̹
    -0.88
     radically
    -0.88
    氏の
    -0.86
     literally
    -0.85
     nutrientes
    -0.85
     amusing
    -0.85
    Ő
    -0.84
    assertArray
    -0.84
     even
    -0.83
    POSITIVE LOGITS
     utilisateur
    1.12
    searching
    1.04
    several
    1.02
     KAY
    0.94
    flights
    0.93
    likopter
    0.92
    generally
    0.91
     aiuta
    0.90
     pesso
    0.90
     proposto
    0.90
    Activations Density 0.010%

    No Known Activations