© 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. 129892
    Prev
    Next
    INDEX
    Explanations

    journal references

    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
     of
    -1.23
     here
    -1.20
    newswire
    -1.06
     dunque
    -1.00
    纠结
    -0.96
    Y
    -0.92
     isn
    -0.92
     wasn
    -0.90
    livejournal
    -0.90
     a
    -0.90
    POSITIVE LOGITS
     ucran
    1.37
     japones
    1.26
     élas
    1.10
     femelle
    1.09
     japonais
    1.09
    鵡
    1.07
    iteln
    1.07
    Adres
    1.06
     labdar
    1.05
    weitere
    1.05
    Activations Density 0.003%

    No Known Activations