© 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. 20960
    Prev
    Next
    INDEX
    Explanations

    tangible, palpable, and tactile concepts

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

    The neuron detects words denoting physical or tactile properties (e.g. “tangible,” “palpable,” “tactile,” “nonpalpable,” etc.).

    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
    沵
    -2.48
    sukienka
    -2.47
    bluza
    -2.44
    糁
    -2.44
     exceedingly
    -2.34
    摀
    -2.34
     ´
    -2.33
    鵙
    -2.27
     certamente
    -2.25
    untuk
    -2.23
    POSITIVE LOGITS
    \
    2.81
     provide
    2.19
     листья
    2.17
     tangible
    2.11
     epitom
    2.02
    ൩
    1.99
    "
    1.98
     started
    1.95
     establish
    1.95
    Usually
    1.92
    Activations Density 0.004%

    No Known Activations