© 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-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-65K
    7. 6949
    Prev
    Next
    INDEX
    Explanations

    learning tutorials

    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_65k_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
    嶂
    0.88
     الإسلام
    0.80
     služby
    0.80
    容器
    0.78
    ujemy
    0.77
     कंटे
    0.75
    プレート
    0.75
    Ᏺ
    0.73
     windscreen
    0.73
    处理器
    0.72
    POSITIVE LOGITS
    сього
    0.76
     complacent
    0.72
     tions
    0.72
     kus
    0.71
     fellow
    0.70
     Beaux
    0.70
     -----
    0.70
     Fellow
    0.69
     des
    0.69
     avanc
    0.69
    Activations Density 0.005%

    No Known Activations