© 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. 64072
    Prev
    Next
    INDEX
    Explanations

    OPEN GAME license

    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
     youth
    -0.75
    SPECT
    -0.74
     Youth
    -0.70
     Comedy
    -0.70
     Shoulders
    -0.69
     ASI
    -0.69
    Wedding
    -0.69
    assertArray
    -0.69
     Cooler
    -0.68
    Ladder
    -0.68
    POSITIVE LOGITS
     Vor
    1.03
     Dela
    1.00
     Fortune
    1.00
    Vor
    0.98
    ドロ
    0.94
    vor
    0.87
     Visibility
    0.85
     sweep
    0.84
     vor
    0.84
    Dela
    0.84
    Activations Density 0.057%

    No Known Activations