© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 58901
    Prev
    Next
    INDEX
    Explanations

    Tow and Tou with suffixes

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

    The neuron activates on tokens containing the character sequence “tou” (including “tow”), effectively flagging any word or fragment beginning with those letters.

    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
    𝙊
    -0.85
     kep
    -0.84
    luci
    -0.84
     colectivo
    -0.81
    finally
    -0.80
     verranno
    -0.76
     finally
    -0.75
    äger
    -0.74
     FINALLY
    -0.71
     dayan
    -0.71
    POSITIVE LOGITS
     hair
    0.84
    食べた
    0.78
     Send
    0.77
     Tow
    0.72
    gaard
    0.71
     droop
    0.71
     Tou
    0.70
    headed
    0.69
    nson
    0.69
     Hair
    0.68
    Activations Density 0.014%

    No Known Activations