© 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. 130660
    Prev
    Next
    INDEX
    Explanations

    controlling and diversity

    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
    utiliz
    -1.38
    Ө
    -1.28
    órica
    -1.28
    痉
    -1.26
     carreaux
    -1.25
    effectively
    -1.22
     розпові
    -1.20
    somewhat
    -1.18
     boî
    -1.17
     clamor
    -1.16
    POSITIVE LOGITS
     but
    1.32
     many
    1.29
     by
    1.15
     jedoch
    1.14
     azonban
    1.13
     utafiti
    1.11
     even
    1.10
     quickly
    1.10
     however
    1.09
     však
    1.09
    Activations Density 0.120%

    No Known Activations