© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 38266
    Prev
    Next
    INDEX
    Explanations

    names of rivers, creeks, and streams

    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_22/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
     delantero
    -1.41
    already
    -1.30
     représenter
    -1.28
    actually
    -1.23
    貼り
    -1.21
     your
    -1.20
     insanely
    -1.20
     compromisos
    -1.18
    your
    -1.18
     atractivo
    -1.17
    POSITIVE LOGITS
     during
    1.47
     throughout
    1.38
    chauen
    1.37
     water
    1.35
     and
    1.30
     until
    1.30
     in
    1.29
     has
    1.29
     through
    1.25
     river
    1.22
    Activations Density 0.059%

    No Known Activations