© 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. 2831
    Prev
    Next
    INDEX
    Explanations

    numbers and version numbers

    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
     again
    -1.95
    again
    -1.44
     опять
    -1.28
     novamente
    -1.23
    Again
    -1.22
     다시
    -1.21
     opět
    -1.19
     ponownie
    -1.13
     Again
    -1.12
     lại
    -1.07
    POSITIVE LOGITS
     first
    1.17
    These
    1.12
    cyclopedia
    1.02
    besondere
    0.98
    ądz
    0.97
     These
    0.96
    แรก
    0.96
     these
    0.94
     if
    0.94
     only
    0.93
    Activations Density 0.055%

    No Known Activations