© 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. 33882
    Prev
    Next
    INDEX
    Explanations

    Circumvention, Anterior chamber, Q

    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
     first
    -1.42
     has
    -1.40
     h
    -1.31
     l
    -1.31
     P
    -1.30
     time
    -1.27
     t
    -1.25
     v
    -1.22
     took
    -1.20
     J
    -1.16
    POSITIVE LOGITS
     verhind
    1.55
     constater
    1.50
     besonder
    1.33
     nimmer
    1.33
     pittores
    1.30
     parfü
    1.28
     trám
    1.27
     faciliter
    1.26
     kulinar
    1.25
     fiables
    1.25
    Activations Density 0.000%

    No Known Activations