© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 11473
    Prev
    Next
    INDEX
    Explanations

    each respective particular

    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
    ulco
    -1.02
    ╞
    -0.97
    Charsets
    -0.97
     and
    -0.95
     two
    -0.94
    dette
    -0.92
    >());
    -0.92
    ]=\
    -0.91
    óis
    -0.91
    árqu
    -0.90
    POSITIVE LOGITS
     each
    2.27
     respective
    1.60
    each
    1.55
     jeweiligen
    1.50
     particular
    1.44
    Each
    1.43
    それぞれの
    1.28
     ciasc
    1.20
     poszczegól
    1.18
     kyse
    1.18
    Activations Density 0.081%

    No Known Activations