© 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. 67809
    Prev
    Next
    INDEX
    Explanations

    noun followed by "are" or "is"

    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
     waarschijnlijk
    -1.16
     that
    -1.06
     vervolgens
    -1.05
     Cuando
    -1.03
     daarbij
    -1.02
     unserer
    -1.01
    .
    -1.01
     nuestra
    -1.01
     eigenlijk
    -1.00
     our
    -1.00
    POSITIVE LOGITS
     also
    1.31
     suporta
    1.27
     continue
    1.19
    www
    1.16
     damen
    1.14
     übrigens
    1.13
     wens
    1.12
     zui
    1.12
     continuer
    1.11
    IVENESS
    1.11
    Activations Density 0.010%

    No Known Activations