© 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. 66570
    Prev
    Next
    INDEX
    Explanations

    " . " " , "

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

    The neuron is primarily activated by numeric tokens and words that carry measurable/statistical values (e.g. digits and related quantitative markers).

    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
    你的
    -0.95
    因為
    -0.94
     你
    -0.93
    比如
    -0.93
     فقط
    -0.91
    方法
    -0.91
     Gré
    -0.90
     téléchargement
    -0.90
    随着
    -0.89
    alot
    -0.89
    POSITIVE LOGITS
     also
    1.65
     further
    1.59
     or
    1.55
     perhaps
    1.47
     this
    1.37
     possibly
    1.26
     Further
    1.16
     may
    1.13
     support
    1.12
     zároveň
    1.09
    Activations Density 0.032%

    No Known Activations