© 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. 22-GEMMASCOPE-RES-131K
    7. 14043
    Prev
    Next
    INDEX
    Explanations

    observing surroundings

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

    The neuron fires on verbs and phrases that denote looking closely, examining, analyzing, or otherwise inspecting and attending to details.

    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
    jacency
    -1.05
     you
    -1.00
     that
    -0.99
     misunderstand
    -0.99
    awakeFromNib
    -0.96
     itulah
    -0.96
    daging
    -0.96
    ální
    -0.94
     explaining
    -0.93
    negara
    -0.91
    POSITIVE LOGITS
    possible
    0.96
    grew
    0.96
    льном
    0.96
    wrote
    0.96
    tonne
    0.93
     целом
    0.93
     Потом
    0.91
    vaila
    0.91
     surroundings
    0.91
    oher
    0.91
    Activations Density 0.010%

    No Known Activations