© 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. 39878
    Prev
    Next
    INDEX
    Explanations

    nonzero operand, proper, remaining

    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
     except
    -1.78
    以外は
    -1.32
     unless
    -1.31
     Except
    -1.30
    Except
    -1.14
     кроме
    -1.05
    以外の
    -1.02
    except
    -1.01
     sauf
    -0.98
    除了
    -0.97
    POSITIVE LOGITS
     monaster
    0.85
    ---------------
    0.82
    ih
    0.82
     экскур
    0.81
    Dw
    0.81
     TypeError
    0.80
    seg
    0.79
    Wpf
    0.79
     Goddard
    0.79
    Mahon
    0.79
    Activations Density 0.038%

    No Known Activations