© 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. 10-GEMMASCOPE-RES-131K
    4. 104472
    Prev
    Next
    INDEX
    Explanations

    separators followed by specific words

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

    The neuron fires strongly on the prime‐notation pieces in biochemical names (e.g. the “3’,” “5’-” and related tokens in “3′,5′‐cyclic monophosphate”).

    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
     that
    -2.19
     of
    -2.08
     to
    -1.88
    in
    -1.60
    to
    -1.60
    represents
    -1.48
    _
    -1.48
     bislang
    -1.43
    seemed
    -1.43
    end
    -1.41
    POSITIVE LOGITS
    tisgarh
    2.00
    :✨
    1.97
    ]")]
    1.66
     quien
    1.66
    upyter
    1.62
     PUSTAKA
    1.60
     estatu
    1.60
     prata
    1.59
    __':
    
    1.59
    titudes
    1.56
    Activations Density 0.252%

    No Known Activations