© 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. 13787
    Prev
    Next
    INDEX
    Explanations

    questions and 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
     to
    -1.26
    trie
    -1.11
     —
    -1.09
    风
    -1.09
     by
    -1.09
     THE
    -1.08
     –
    -1.07
    ='
    -1.05
     through
    -1.04
     含
    -1.04
    POSITIVE LOGITS
    França
    1.23
    њи
    1.16
    edere
    1.16
    Какво
    1.12
    Анна
    1.09
    メモリ
    1.07
     délais
    1.06
     origini
    1.03
    对话框
    1.03
     besoins
    1.02
    Activations Density 0.000%

    No Known Activations