© 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-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 2573
    Prev
    Next
    INDEX
    Explanations

    com complicated

    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
    кол
    0.90
    amp
    0.90
    га
    0.89
    אות
    0.86
    ंती
    0.84
    
    0.84
     kurt
    0.83
     Pes
    0.81
    𝑖
    0.79
    𝑦
    0.78
    POSITIVE LOGITS
    fasterxml
    1.47
    netfx
    1.41
    unications
    1.34
    aderie
    1.34
    ouflage
    1.28
    ्युनिकेशन
    1.25
    ၻ
    1.24
    noof
    1.21
    badlogic
    1.21
    oufl
    1.19
    Activations Density 0.271%

    No Known Activations