© 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. 33756
    Prev
    Next
    INDEX
    Explanations

    court of appeals circuits

    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
     and
    -1.48
     bepaalde
    -1.20
     verschill
    -1.20
    グルト
    -1.18
    Quels
    -1.17
     duidelijk
    -1.15
     ontwikkel
    -1.12
    Où
    -1.11
    Réponse
    -1.09
     hetzelfde
    -1.09
    POSITIVE LOGITS
    in
    1.38
     stanovnika
    1.16
     “
    1.11
    ā
    1.06
    _
    1.06
     Grüßen
    1.05
    )}
    1.02
    ay
    1.02
     heridos
    1.02
    from
    1.01
    Activations Density 0.009%

    No Known Activations