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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 101156
    Prev
    Next
    INDEX
    Explanations

    programming and technical terms

    np_acts-logits-general · gemini-2.5-flash-lite

    Looking at the activations, I can see high activation values for: - "try" (64.5) in the context of "give Scuba Diving a try" - "errors" (39) in programming/import context - "good use" (42.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    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
     from
    -1.48
     všechny
    -1.37
     through
    -1.33
    '
    -1.28
     "
    -1.27
     всех
    -1.24
     a
    -1.24
     there
    -1.22
     '
    -1.21
     EVERY
    -1.18
    POSITIVE LOGITS
     also
    2.00
    也就
    1.56
     others
    1.52
    龵
    1.49
     few
    1.46
     dezelve
    1.45
     également
    1.43
     також
    1.40
    N
    1.40
    </strong>
    1.38
    Activations Density 0.068%

    No Known Activations