© 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. 36583
    Prev
    Next
    INDEX
    Explanations

    when or even

    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
     обязательно
    -1.19
    asticity
    -1.05
     finalmente
    -1.05
    剋
    -1.04
     hadde
    -1.02
    合适
    -1.00
     março
    -0.96
    Katso
    -0.95
     kilom
    -0.94
    өз
    -0.94
    POSITIVE LOGITS
     entire
    1.30
     when
    1.30
     avião
    1.28
     braço
    1.22
     espelho
    1.20
     cuando
    1.19
     even
    1.19
     several
    1.18
     jogador
    1.17
     himself
    1.16
    Activations Density 0.007%

    No Known Activations