© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 43361
    Prev
    Next
    INDEX
    Explanations

    words ending in aly

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

    The neuron responds to the character sequence “aly” in tokens (e.g. in words like macrocephaly, hepatomegaly, acromegaly, dialysis, Daly).

    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
     However
    -2.98
     Their
    -2.77
     แต่
    -2.56
    龊
    -2.56
     téc
    -2.53
     amenaz
    -2.53
     Now
    -2.50
     And
    -2.48
     развитие
    -2.45
     Jetzt
    -2.39
    POSITIVE LOGITS
    1
    4.34
    4
    3.08
    {
    2.95
    7
    2.92
    0
    2.84
    3
    2.78
    re
    2.63
    When
    2.59
    aly
    2.53
    e
    2.50
    Activations Density 0.010%

    No Known Activations