© 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. 58405
    Prev
    Next
    INDEX
    Explanations

    grid and pack methods

    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
    Intended
    -0.85
    SaveSave
    -0.74
     berp
    -0.73
    ┕
    -0.73
    Ours
    -0.71
    pushd
    -0.69
    OwnerId
    -0.68
     ungkap
    -0.68
    UNICEF
    -0.68
    Воспита
    -0.68
    POSITIVE LOGITS
    pack
    1.40
    grid
    1.34
     pack
    1.34
     packing
    1.29
     grid
    1.27
     place
    1.16
    PACK
    1.16
    config
    1.13
    Pack
    1.13
     grids
    1.13
    Activations Density 0.012%

    No Known Activations