© 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-16K
    7. 7015
    Prev
    Next
    INDEX
    Explanations

    David followed by a surname

    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_16k_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
    ammonium
    1.14
    럴
    1.07
    topLeft
    1.01
     Infect
    0.99
     tortillas
    0.99
     Jewish
    0.99
    𝐝
    0.99
     RPS
    0.98
    级的
    0.97
    แรม
    0.97
    POSITIVE LOGITS
    heiser
    1.39
    ونة
    1.17
     omitted
    1.12
    Всем
    1.00
     señalado
    0.99
    ්
    0.98
    ння
    0.96
    Gpio
    0.95
     persönlich
    0.95
    വം
    0.94
    Activations Density 0.031%

    No Known Activations