© 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. 68544
    Prev
    Next
    INDEX
    Explanations

    rare/infrequent occurrences

    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
    tivität
    -0.88
    ELINE
    -0.81
    sique
    -0.76
     embarrassment
    -0.76
    essor
    -0.75
    спе
    -0.75
    assi
    -0.69
    ANCER
    -0.69
    bagai
    -0.68
    tinger
    -0.68
    POSITIVE LOGITS
    rare
    1.02
     rarest
    0.99
    Rare
    0.98
     siquiera
    0.96
     rarity
    0.95
     RARE
    0.95
     rare
    0.94
     raras
    0.91
     raro
    0.90
     requiere
    0.89
    Activations Density 0.042%

    No Known Activations