© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 67519
    Prev
    Next
    INDEX
    Explanations

    making statements or responding

    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
     from
    -1.25
     there
    -1.14
     between
    -1.12
     even
    -1.10
     sogar
    -1.08
     semasa
    -1.08
     because
    -1.06
     especially
    -1.03
     &&
    -1.02
     terutama
    -1.02
    POSITIVE LOGITS
     response
    1.55
     responded
    1.45
     said
    1.38
     however
    1.32
     respond
    1.27
    回應
    1.26
     responds
    1.15
     reply
    1.14
     replied
    1.10
     claim
    1.09
    Activations Density 0.034%

    No Known Activations