© 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. 14065
    Prev
    Next
    INDEX
    Explanations

    gas technical contexts

    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
    퐸
    -3.08
    鸶
    -2.86
    髕
    -2.44
    媜
    -2.44
    屣
    -2.39
    都已经
    -2.36
    𐐀
    -2.36
    堙
    -2.33
    they
    -2.28
    尛
    -2.28
    POSITIVE LOGITS
     failings
    2.19
     inextrica
    2.16
     memutus
    2.06
     เขา
    2.06
     sebaiknya
    2.03
     białe
    2.02
     resurrect
    1.99
     sagging
    1.95
     upheaval
    1.95
     ['./
    1.93
    Activations Density 0.028%

    No Known Activations