© 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. 62978
    Prev
    Next
    INDEX
    Explanations

    dense and sparse matrix computation

    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
    mitives
    -0.84
     Raub
    -0.69
     gedaan
    -0.69
    尤
    -0.68
    metries
    -0.68
     cây
    -0.68
     liebe
    -0.67
     Baba
    -0.66
     Fitzpatrick
    -0.66
    encephal
    -0.65
    POSITIVE LOGITS
     sparse
    1.99
    sparse
    1.73
     spars
    1.73
    Sparse
    1.63
     Sparse
    1.60
     dense
    1.47
    dense
    1.41
     density
    1.36
     CSR
    1.25
    CSR
    1.24
    Activations Density 0.028%

    No Known Activations