© 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. 10-GEMMASCOPE-RES-131K
    7. 21962
    Prev
    Next
    INDEX
    Explanations

    prepulse inhibition

    np_acts-logits-general · gemini-2.5-flash-lite

    numbers or numerical identifiers in documents, particularly years, version numbers, and catalog numbers.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    the presence of standalone numeric tokens (years, list indices, and other numbers) in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     However
    -2.41
     When
    -2.39
     geringen
    -2.19
     leichten
    -2.19
     Cualquier
    -2.09
     gleaming
    -2.06
    zeppelin
    -2.06
     wichtigen
    -2.03
     Verständnis
    -2.03
     Selecciona
    -2.02
    POSITIVE LOGITS
    m
    2.83
    in
    2.20
    
    2.19
     dezelve
    2.16
    ()]);
    2.14
    茕
    2.08
    et
    2.03
    ad
    2.02
    
    2.02
     vru
    1.98
    Activations Density 0.000%

    No Known Activations