© 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. 84126
    Prev
    Next
    INDEX
    Explanations

    change and unchanged states

    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
    -1.37
     pantaloni
    -1.24
    これは
    -1.16
     imprimé
    -1.09
     ceva
    -1.06
    ARTER
    -1.05
     không
    -1.04
    一些
    -1.03
    ちょっと
    -1.01
    erdings
    -1.01
    POSITIVE LOGITS
     except
    2.05
     nor
    1.55
    except
    1.50
     or
    1.47
     change
    1.45
     unless
    1.45
     until
    1.41
     unchanged
    1.40
     from
    1.34
     since
    1.33
    Activations Density 0.037%

    No Known Activations