© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 80899
    Prev
    Next
    INDEX
    Explanations

    describing appearance and state

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

    The neuron fires on occurrences of “look” (and its inflected forms like looks, looked, looking) describing appearance.

    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
    rée
    -1.02
    nological
    -1.02
    imetry
    -1.01
    strahlung
    -1.01
    wicz
    -1.00
    sitive
    -0.99
    raining
    -0.96
    ogical
    -0.96
    iamo
    -0.95
    .‏
    -0.95
    POSITIVE LOGITS
     like
    1.53
     relaxed
    1.27
     upset
    1.16
     happy
    1.11
     fatigue
    1.10
     as
    1.06
     tired
    1.03
     pleased
    1.02
     ready
    1.02
     more
    1.01
    Activations Density 0.019%

    No Known Activations