© 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. 74697
    Prev
    Next
    INDEX
    Explanations

    about things and matters

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

    The neuron activates on prepositions (especially “of,” “to,” “on,” and “about”) that head common multi-word phrases (e.g. “sign of,” “speaks to,” “volumes about,” “comment on”).

    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
    iocene
    -1.76
     agresión
    -1.66
    ⎆
    -1.60
    ഞ
    -1.45
    がありますが
    -1.44
     through
    -1.44
     like
    -1.43
    悽
    -1.43
     across
    -1.42
    áncer
    -1.42
    POSITIVE LOGITS
     how
    1.76
    5
    1.66
     
    1.61
    T
    1.53
    8
    1.48
    s
    1.39
    rd
    1.37
    P
    1.36
     イラストレーション
    1.35
    K
    1.35
    Activations Density 0.021%

    No Known Activations