© 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. 22-GEMMASCOPE-RES-131K
    4. 79755
    Prev
    Next
    INDEX
    Explanations

    medical and technical terms

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

    numerical values and digits.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron predominantly activates on numeric tokens (i.e. standalone numbers or quantities).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     natin
    -0.93
    Associ
    -0.83
    *</
    -0.81
     Associ
    -0.81
     Asso
    -0.81
     usw
    -0.79
     Quaternary
    -0.79
    ҽ
    -0.78
    feliz
    -0.78
    коле
    -0.77
    POSITIVE LOGITS
     cubre
    0.99
     cierra
    0.86
     fuel
    0.82
     Abuse
    0.81
     credit
    0.81
     Themen
    0.81
    ferrer
    0.81
     Against
    0.79
    ursos
    0.79
     dogs
    0.78
    Activations Density 0.000%

    No Known Activations