© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 10825
    Prev
    Next
    INDEX
    Explanations

    else or other words

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

    The neuron primarily detects numeric tokens (digits, numeric values, and related symbols like “$”).

    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
    Xl
    -1.02
    uração
    -0.87
    mäs
    -0.85
    mā
    -0.84
    RAV
    -0.84
    ensiva
    -0.83
    iniai
    -0.82
    ţă
    -0.81
     bará
    -0.81
    võ
    -0.81
    POSITIVE LOGITS
     other
    2.53
    其他
    2.08
     остальных
    2.05
     otherwise
    2.03
    其它
    2.03
    その他
    1.95
     others
    1.91
     autres
    1.91
     demás
    1.86
    otherwise
    1.85
    Activations Density 0.049%

    No Known Activations