© 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. 64160
    Prev
    Next
    INDEX
    Explanations

    code and specific terms like delivery

    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
    BERN
    -0.82
     SPOT
    -0.77
    boats
    -0.76
    ueltos
    -0.75
    SPOT
    -0.75
    stamo
    -0.75
    idata
    -0.75
     balle
    -0.74
    questa
    -0.73
    τού
    -0.73
    POSITIVE LOGITS
     span
    1.20
     &
    1.16
     ${({
    1.09
     &,
    1.08
    ${
    1.02
     @
    0.98
     &.
    0.96
     &[
    0.95
     '&
    0.93
    &
    0.92
    Activations Density 0.012%

    No Known Activations