© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 65081
    Prev
    Next
    INDEX
    Explanations

    and or

    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
     these
    -1.50
     both
    -1.45
     particularly
    -1.41
     especially
    -1.36
     not
    -1.34
     despite
    -1.26
     getting
    -1.24
     mainly
    -1.23
     too
    -1.23
     this
    -1.16
    POSITIVE LOGITS
    actually
    1.38
    颔
    1.28
    靣
    1.25
    摇了摇头
    1.24
     😁
    1.24
    zaak
    1.23
    不由得
    1.22
    戋
    1.20
    忐
    1.20
    Thats
    1.19
    Activations Density 0.107%

    No Known Activations