© 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. 10-GEMMASCOPE-RES-131K
    7. 14963
    Prev
    Next
    INDEX
    Explanations

    describing outcomes or states

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

    The neuron activates on numeric or quantitative expressions—counts, measurements, rates, and other statistical figures.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     and
    -2.08
     však
    -1.66
     however
    -1.59
     jedoch
    -1.52
     kuitenkin
    -1.43
     azonban
    -1.43
     a
    -1.42
    However
    -1.37
     these
    -1.34
    These
    -1.30
    POSITIVE LOGITS
     that
    2.06
    踯
    1.50
     quello
    1.49
     datter
    1.45
     its
    1.44
    takings
    1.42
    着脸
    1.37
     entsprechenden
    1.37
    zony
    1.36
    媼
    1.34
    Activations Density 0.614%

    No Known Activations