© 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. 39650
    Prev
    Next
    INDEX
    Explanations

    experience and related words

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

    The neuron strongly activates on occurrences of the word “experience” (and its close variants) especially when used as a heading or key topic label.

    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
     the
    -2.33
    盦
    -1.84
     氏
    -1.59
     enlace
    -1.51
    臏
    -1.51
     utiliser
    -1.48
     জন্য
    -1.46
    the
    -1.41
     meningkatkan
    -1.40
    '
    -1.39
    POSITIVE LOGITS
     experience
    2.16
     experiences
    2.05
     experiencias
    1.72
    wiście
    1.68
     whatnot
    1.66
    .
    1.65
     條
    1.63
     鐵
    1.59
    idk
    1.58
     層
    1.55
    Activations Density 0.046%

    No Known Activations