© 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. 71768
    Prev
    Next
    INDEX
    Explanations

    appositives and clauses

    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
     naprawdę
    -1.29
     malheureusement
    -1.21
     possiamo
    -1.20
     meille
    -1.20
    になるので
    -1.19
     caminhão
    -1.18
     rayures
    -1.17
     vrais
    -1.16
    weren
    -1.16
     télécharger
    -1.15
    POSITIVE LOGITS
     also
    1.77
     said
    1.39
     will
    1.31
     has
    1.27
     says
    1.25
     first
    1.25
     was
    1.23
     is
    1.22
     didn
    1.20
     spent
    1.20
    Activations Density 0.039%

    No Known Activations