© 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. 16-GEMMASCOPE-2-RES-262K
    7. 120739
    Prev
    Next
    INDEX
    Explanations

    neither incur loss

    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_16_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
    are
    0.80
    W
    0.76
    ра
    0.71
    га
    0.70
    ן
    0.68
    на
    0.68
    ਾ
    0.68
     ७
    0.68
    У
    0.66
    Ва
    0.63
    POSITIVE LOGITS
    も
    0.64
     car
    0.63
     in
    0.59
    さすが
    0.57
     rearview
    0.56
     crew
    0.55
    했다
    0.55
     carb
    0.55
     Philippines
    0.55
     shrimp
    0.55
    Activations Density 0.000%

    No Known Activations