© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 68458
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     for
    -1.21
     like
    -1.12
     receive
    -1.09
    NÉ
    -1.05
    =(-
    -1.05
     five
    -1.04
     eight
    -1.03
    Ѕ
    -1.03
     most
    -1.01
    🕺
    -1.01
    POSITIVE LOGITS
    Bereich
    1.41
    了下去
    1.40
     tyto
    1.34
    Stap
    1.25
     ARISING
    1.23
    Utilisation
    1.20
    Typo
    1.17
    Begriff
    1.17
     mangiare
    1.16
    Forked
    1.16
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.