© 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. 10-GEMMASCOPE-RES-131K
    7. 113565
    Prev
    Next
    INDEX
    Explanations

    the word too

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

    The neuron strongly activates on the adverb “too,” flagging instances of that intensifier.

    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
    䊐
    -2.06
    ان
    -1.98
    re
    -1.80
     &
    -1.73
    
    -1.66
    lgari
    -1.65
    ቍ
    -1.64
     curtail
    -1.63
     to
    -1.63
    ൎ
    -1.59
    POSITIVE LOGITS
     hornear
    1.63
     pretends
    1.61
     müßte
    1.59
    おかげ
    1.58
    何故
    1.56
    These
    1.55
     möge
    1.55
    Usually
    1.51
     lakier
    1.49
     feiert
    1.49
    Activations Density 0.010%

    No Known Activations