© 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. 47550
    Prev
    Next
    INDEX
    Explanations

    hexadecimal identifiers and file paths

    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
     while
    -1.49
     with
    -1.27
     those
    -1.27
     during
    -1.25
     on
    -1.23
     While
    -1.22
     without
    -1.21
     many
    -1.20
     just
    -1.20
     or
    -1.15
    POSITIVE LOGITS
     zwi
    1.16
     mêmes
    1.15
     EVEN
    1.11
    Directeur
    1.04
     BECAUSE
    1.04
     soooo
    1.03
     ferocious
    1.02
     verrou
    1.00
    Hmmm
    1.00
    こんな
    1.00
    Activations Density 0.001%

    No Known Activations