© 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. 36648
    Prev
    Next
    INDEX
    Explanations

    describing phrases

    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
     incredi
    -1.14
     impecable
    -1.13
     suspic
    -1.11
     cultiv
    -1.05
     ingenu
    -1.05
     brill
    -1.04
     effici
    -1.03
     discer
    -1.02
     exces
    -1.01
     repug
    -1.01
    POSITIVE LOGITS
     a
    1.83
     an
    1.46
     mezi
    1.16
     márm
    1.13
    Ngay
    1.10
     or
    1.09
    Muito
    1.08
     retten
    1.03
     tussen
    0.99
    ьому
    0.99
    Activations Density 0.042%

    No Known Activations