© 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. 34-GEMMASCOPE-RES-131K
    7. 110473
    Prev
    Next
    INDEX
    Explanations

    or followed by alternatives

    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_34/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
     also
    -1.52
    vereign
    -1.37
    .‏
    -1.23
    嚀
    -1.23
     również
    -1.20
    也在
    -1.19
    圌
    -1.19
     также
    -1.17
     também
    -1.13
     También
    -1.13
    POSITIVE LOGITS
     rather
    3.23
    Rather
    2.52
     Rather
    2.27
     vielmehr
    2.20
    rather
    2.20
     plutôt
    2.08
     raczej
    2.06
     more
    2.03
     at
    1.96
     piuttosto
    1.95
    Activations Density 0.051%

    No Known Activations