© 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. 10-GEMMASCOPE-RES-131K
    7. 85984
    Prev
    Next
    INDEX
    Explanations

    Lenovo, mathematics, Informa PLC

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

    The neuron detects unusually long alphanumeric tokens—i.e. long words or identifiers.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    已是
    -2.44
     orologio
    -2.39
     renowned
    -2.38
    錞
    -2.31
    }
    -2.30
    𞤢
    -2.27
     weihnachten
    -2.25
     is
    -2.25
     This
    -2.16
    となって
    -2.16
    POSITIVE LOGITS
    ם
    2.55
    izations
    2.28
    靫
    2.23
    撺
    2.17
    蟜
    2.13
     anaesthesia
    2.13
    
    2.09
    cześ
    2.08
     téléphone
    2.00
    ጐ
    2.00
    Activations Density 0.003%

    No Known Activations