© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 29259
    Prev
    Next
    INDEX
    Explanations

    safe and appropriate

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_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
     ਅਤੇ
    0.49
    ਬ
    0.48
    दे
    0.46
    สาว
    0.46
    ਜ
    0.46
    ਤਾ
    0.45
    ⠑
    0.44
    гі
    0.43
    敵人
    0.43
    ૈ
    0.42
    POSITIVE LOGITS
     YoY
    0.47
     Puoi
    0.46
     accumulating
    0.43
     podrás
    0.41
    各自
    0.40
     computation
    0.39
     bitmap
    0.39
     synchronous
    0.38
     XOR
    0.38
     totaling
    0.37
    Activations Density 0.002%

    No Known Activations