© 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. 34618
    Prev
    Next
    INDEX
    Explanations

    academic thesis or technical terms

    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
     benzin
    -1.52
     antik
    -1.46
     mikrofon
    -1.44
     optik
    -1.42
     kamera
    -1.38
     stadion
    -1.37
     karbon
    -1.34
     kapital
    -1.32
     fabrik
    -1.29
     seksual
    -1.27
    POSITIVE LOGITS
     and
    1.72
    It
    1.43
    1.40
    This
    1.29
    At
    1.23
     a
    1.21
    During
    1.20
    If
    1.18
    When
    1.16
     acest
    1.15
    Activations Density 0.006%
    No Known Activations