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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 67139
    Prev
    Next
    INDEX
    Explanations

    Aging alters visual processing

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

    ISBN numbers in book or publication citations.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
     in
    -1.34
    為に
    -1.09
     by
    -1.08
     on
    -1.08
    уре
    -1.04
    kese
    -1.02
    bunga
    -1.02
    板上
    -1.01
    ()},
    -1.01
    🤟
    -1.00
    POSITIVE LOGITS
    Allgemeine
    1.30
    Aufbau
    1.27
    Recept
    1.27
    这些
    1.17
    トッピング
    1.16
    Konto
    1.14
    Intérieur
    1.13
    Unternehmen
    1.12
    Zutaten
    1.12
     segni
    1.11
    Activations Density 0.002%

    No Known Activations