© 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. 57529
    Prev
    Next
    INDEX
    Explanations

    "too" followed by punctuation

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

    The neuron fires strongly on the adverb “too,” marking tokens that add an “also/likewise” emphasis.

    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
     also
    -1.30
    reportError
    -1.01
     again
    -1.01
     and
    -1.00
    䊐
    -0.95
    ⮜
    -0.94
    tización
    -0.93
     также
    -0.92
    ÇÕES
    -0.90
    ࿊
    -0.90
    POSITIVE LOGITS
    Sometimes
    1.14
    Now
    1.13
    They
    1.13
    もちろん
    1.12
    Among
    1.09
    Those
    1.08
    Many
    1.08
    The
    1.07
    各种
    1.06
    That
    1.05
    Activations Density 0.009%

    No Known Activations