© 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. 22-GEMMASCOPE-RES-131K
    7. 34211
    Prev
    Next
    INDEX
    Explanations

    author herein, seasons, fields, analysis

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

    The neuron is tuned to pick out formal, multi‐syllabic content words (e.g. “arguments,” “framework,” “revocation”) typical of academic or technical discourse.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    事が
    -1.01
     trwa
    -0.96
    事も
    -0.95
    iconque
    -0.91
     tiszt
    -0.90
    ℉
    -0.90
     никаких
    -0.90
    both
    -0.89
     prowadzi
    -0.88
    何度も
    -0.87
    POSITIVE LOGITS
     nila
    1.01
     from
    0.86
    gebnis
    0.84
     cursive
    0.81
    getUserInfo
    0.81
    ੧
    0.79
     diren
    0.79
     Elegance
    0.79
    ovy
    0.78
    tonsoft
    0.78
    Activations Density 0.138%

    No Known Activations