© 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. 10962
    Prev
    Next
    INDEX
    Explanations

    the event

    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
    новение
    -1.21
     Consejos
    -1.17
    珦
    -1.11
    lecteur
    -1.08
     here
    -1.06
    麁
    -1.03
    itern
    -1.03
     pán
    -1.02
    niająca
    -1.02
    neuri
    -1.01
    POSITIVE LOGITS
    擁有
    1.24
    وفق
    1.22
     вони
    1.19
    ícias
    1.16
    这是
    1.09
    yship
    1.05
    쿡
    1.05
    ಝ
    1.05
     feat
    1.04
     ordeal
    1.03
    Activations Density 0.040%

    No Known Activations