© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 28965
    Prev
    Next
    INDEX
    Explanations

    signal to

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

    The neuron activates on words denoting nonverbal signaling or gesture actions (e.g. “motion,” “gesturing,” “beckoned,” “signalling”).

    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
    )」
    -1.93
    菔
    -1.72
     there
    -1.68
    衚
    -1.61
     eliminates
    -1.53
     rígido
    -1.52
     decoradas
    -1.51
     usata
    -1.51
    )，
    -1.49
     protegido
    -1.49
    POSITIVE LOGITS
     et
    1.88
     pretende
    1.80
     intenta
    1.70
    p
    1.66
    n
    1.65
    ol
    1.63
    er
    1.63
    ed
    1.61
    要做
    1.57
    h
    1.55
    Activations Density 0.005%

    No Known Activations