© 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. 34-GEMMASCOPE-RES-131K
    7. 11894
    Prev
    Next
    INDEX
    Explanations

    parts of words

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

    This neuron consistently lights up on very high‐frequency English tokens (common words like “he,” “for,” “us,” “end,” etc.).

    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
     apenas
    -0.95
     integrados
    -0.88
    もとも
    -0.85
    不但
    -0.84
     continuar
    -0.81
    nette
    -0.79
     anunció
    -0.77
     анали
    -0.77
     aumentar
    -0.77
     กล
    -0.76
    POSITIVE LOGITS
    ginate
    0.96
    rosin
    0.85
    astify
    0.84
     metaphorical
    0.82
     metais
    0.80
     изпол
    0.80
    ying
    0.80
     État
    0.80
    امه
    0.80
    curr
    0.80
    Activations Density 0.122%

    No Known Activations