© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 78144
    Prev
    Next
    INDEX
    Explanations

    words followed by prepositions/adverbials

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

    The neuron fires strongly on content words that start up right after a punctuation boundary (e.g. the first word of a clause or segment following a dash, comma, period, 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
    Movies
    -0.79
    雛
    -0.77
    วัด
    -0.77
     tuya
    -0.74
    gesellschaft
    -0.74
     őket
    -0.73
    澗
    -0.73
    Ami
    -0.73
    จาก
    -0.73
    注文
    -0.72
    POSITIVE LOGITS
     him
    0.79
    ა
    0.79
     उस
    0.73
    食べられる
    0.73
     stre
    0.71
    ೀ
    0.71
    יסט
    0.71
     sour
    0.69
    Blah
    0.69
     res
    0.68
    Activations Density 0.065%

    No Known Activations