© 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. 39592
    Prev
    Next
    INDEX
    Explanations

    Getty Images attribution

    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
     rústico
    -1.19
    って何
    -1.14
     their
    -1.12
    .~(\
    -1.09
     decorativo
    -1.09
     זמן
    -1.08
     với
    -1.06
     bricolaje
    -1.06
     Introduction
    -1.06
     angene
    -1.05
    POSITIVE LOGITS
     and
    1.18
    Imagens
    1.11
     />
    1.08
     확인함
    1.06
    Pontos
    1.05
     uuidv
    1.04
    vatie
    1.01
    quelize
    1.00
    ciaal
    1.00
    Comida
    0.95
    Activations Density 0.009%

    No Known Activations