© 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. 66946
    Prev
    Next
    INDEX
    Explanations

    descriptor followed by category

    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
     consultato
    -1.38
     Boletín
    -1.35
    🤙
    -1.31
     kada
    -1.31
    😸
    -1.28
    ztes
    -1.28
    क्या
    -1.25
     ..............
    -1.24
    sApp
    -1.23
     thomas
    -1.23
    POSITIVE LOGITS
     Glaube
    1.45
     initiatives
    1.39
    さんも
    1.38
     strategies
    1.37
    人也
    1.30
     типу
    1.30
     sophisticated
    1.29
     businesses
    1.28
     уже
    1.27
     nasty
    1.26
    Activations Density 0.178%

    No Known Activations