© 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. 104692
    Prev
    Next
    INDEX
    Explanations

    beanbag, coefficients, fee

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

    This neuron detects very high-frequency tokens (common “stop-word”–style words) across documents.

    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
     any
    -1.00
    就可以了
    -0.95
     cualquier
    -0.93
    momix
    -0.93
     şöyle
    -0.90
    Estima
    -0.90
    Antworten
    -0.90
     anything
    -0.88
    iconductor
    -0.88
    dtp
    -0.88
    POSITIVE LOGITS
    这里是
    1.05
     want
    0.99
    ++;
    0.98
     presumably
    0.90
    ∴
    0.88
    ♀
    0.88
    [];
    0.87
    💞
    0.87
     साल
    0.85
    ⿰
    0.85
    Activations Density 0.009%

    No Known Activations