© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 731
    Prev
    Next
    INDEX
    Explanations

    numbers following punctuation

    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_10/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
     and
    -1.63
     síntesis
    -1.38
     laikā
    -1.37
    让
    -1.31
    把
    -1.30
     anmelden
    -1.30
     either
    -1.28
     queste
    -1.25
     have
    -1.25
    läge
    -1.23
    POSITIVE LOGITS
    (''
    1.31
     ceux
    1.30
    Kolor
    1.29
    ität
    1.29
    彼らは
    1.28
     großem
    1.25
     çünkü
    1.24
     hatta
    1.23
     INVENTION
    1.20
    łgor
    1.19
    Activations Density 0.232%

    No Known Activations