© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 48686
    Prev
    Next
    INDEX
    Explanations

    time of update

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

    The neuron flags numeric expressions and related date/time or “as of” context phrases in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     some
    -0.79
     collections
    -0.72
     essential
    -0.71
     a
    -0.70
     primary
    -0.69
    年に
    -0.69
    "....
    -0.69
    stddef
    -0.69
    OLES
    -0.68
     Umfang
    -0.68
    POSITIVE LOGITS
     writing
    2.63
     publication
    2.38
     publishing
    1.90
     publish
    1.85
     press
    1.84
    writing
    1.81
    publication
    1.75
     write
    1.61
    Publication
    1.54
    Writing
    1.54
    Activations Density 0.017%

    No Known Activations