© 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. 128259
    Prev
    Next
    INDEX
    Explanations

    describing geometric shapes

    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
     acidente
    -1.52
    secta
    -1.34
     pôr
    -1.22
    izung
    -1.20
    titial
    -1.19
    archical
    -1.17
     Además
    -1.17
    Lagos
    -1.15
     Após
    -1.13
    了几
    -1.12
    POSITIVE LOGITS
     shaped
    1.38
     your
    1.35
     parfü
    1.31
     YOUR
    1.30
    ها
    1.30
    ,?
    1.27
    haped
    1.27
     Dateien
    1.27
     automóviles
    1.27
     bedien
    1.26
    Activations Density 0.041%

    No Known Activations