© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 14581
    Prev
    Next
    INDEX
    Explanations

    to some tons

    np_acts-logits-general · gemini-2.5-flash-lite

    arrange objects or sequences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ت
    0.68
    ни
    0.63
    ي
    0.59
    ك
    0.57
    т
    0.55
    י
    0.55
    ת
    0.55
    м
    0.52
    слей
    0.52
    त
    0.52
    POSITIVE LOGITS
     Motor
    0.47
    sw
    0.46
    wa
    0.46
    龙头
    0.45
     बतौर
    0.45
     Hydraulic
    0.44
     Film
    0.44
     Materials
    0.43
    wh
    0.43
     Perform
    0.42
    Activations Density 0.000%

    No Known Activations