© 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. 34-GEMMASCOPE-RES-131K
    7. 99689
    Prev
    Next
    INDEX
    Explanations

    algo prefix

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

    The neuron strongly activates on tokens containing the substring “Algo” (as in “Algorithm,” “Algorithms,” “Algonquin,” etc.), i.e. mentions of “Algo‐” prefixed algorithm or algorithm‐related names.

    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
     ഉ
    -0.87
    gpg
    -0.78
     Cyr
    -0.78
    教训
    -0.76
     gemeins
    -0.76
    是一個
    -0.74
    過去の
    -0.74
     jerk
    -0.74
    半个
    -0.74
     допомогти
    -0.73
    POSITIVE LOGITS
     Alg
    1.50
     alg
    1.37
    alg
    1.26
     algo
    1.23
     ALG
    1.22
     Algorithm
    1.20
    Alg
    1.19
     Algo
    1.14
     algorit
    1.14
     algorithms
    1.13
    Activations Density 0.024%

    No Known Activations