© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 699
    Prev
    Next
    INDEX
    Explanations

    end of sentence 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
     your
    -1.71
     rése
    -1.62
     帅气
    -1.56
    璈
    -1.54
     burada
    -1.52
     famoso
    -1.51
    锨
    -1.51
    ⬈
    -1.47
     elegantes
    -1.47
     stratég
    -1.47
    POSITIVE LOGITS
     and
    1.80
     would
    1.63
    *
    1.56
     encompassing
    1.55
     continued
    1.48
     always
    1.47
     showed
    1.45
     while
    1.45
     albeit
    1.44
     constantly
    1.43
    Activations Density 0.019%

    No Known Activations