© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 113860
    Prev
    Next
    INDEX
    Explanations

    too followed by punctuation

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

    This neuron primarily detects the adverb “too.”

    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
     by
    -2.30
     for
    -2.08
     to
    -2.06
     and
    -2.06
     it
    -1.98
     in
    -1.96
     on
    -1.93
     of
    -1.77
     with
    -1.67
     pekerjaan
    -1.63
    POSITIVE LOGITS
    .
    2.19
     ecológica
    1.98
     atardecer
    1.90
    1.90
     orgánica
    1.89
     territorios
    1.89
     doméstica
    1.80
    之类的
    1.79
    <bos>
    1.77
     elástico
    1.77
    Activations Density 0.010%

    No Known Activations