© 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. 100581
    Prev
    Next
    INDEX
    Explanations

    missing a using directive

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

    phrases indicating something is missing or absent, particularly in error messages asking if the user is missing a directive, reference, or looking for something.

    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
     sucesso
    -1.25
    ként
    -1.25
     seção
    -1.13
     AssemblyVersion
    -1.13
     onOptions
    -1.12
     brez
    -1.11
    erunner
    -1.11
     PyLong
    -1.09
     számára
    -1.08
     klare
    -1.07
    POSITIVE LOGITS
     to
    1.90
     meant
    1.37
     were
    1.30
     apprehended
    1.16
     need
    1.14
     parameters
    1.13
     sedangkan
    1.13
     Dritte
    1.11
     Meanwhile
    1.10
     around
    1.09
    Activations Density 0.056%

    No Known Activations