© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 25365
    Prev
    Next
    INDEX
    Explanations

    signed routes or qr codes

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

    The neuron fires on mentions of security or authentication tokens (e.g. “perishable token,” “reset token,” “activation token”).

    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
    Fully
    -0.96
    iiiiiiii
    -0.95
     основной
    -0.93
     kuu
    -0.93
    George
    -0.93
     pouvons
    -0.92
     other
    -0.91
    Price
    -0.91
     zawsze
    -0.91
    eft
    -0.90
    POSITIVE LOGITS
     created
    1.16
     generated
    1.06
     גרם
    1.05
     creation
    1.04
    発行
    1.02
     welcoming
    1.02
     생성
    1.00
    venser
    1.00
    お試し
    0.98
    Од
    0.96
    Activations Density 0.018%

    No Known Activations