© 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-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-262K
    7. 934
    Prev
    Next
    INDEX
    Explanations

    phone numbers and digits

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_22_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     $+$
    0.94
     +,
    0.86
     $+
    0.84
     guidelines
    0.78
     $)$.
    0.76
     $>$
    0.75
    .\\
    0.75
    +,
    0.74
     +
    0.73
     그리고
    0.71
    POSITIVE LOGITS
     telefone
    1.03
     телефона
    0.97
     telepon
    0.97
    Telefono
    0.95
    Телефон
    0.91
    iphone
    0.91
     telefono
    0.88
    telephone
    0.88
    手机
    0.87
     zipcode
    0.87
    Activations Density 0.009%

    No Known Activations