© 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. 42349
    Prev
    Next
    INDEX
    Explanations

    question initiators

    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
    総合
    0.44
    豇
    0.43
    頜
    0.43
    综合
    0.42
     complicating
    0.41
     landlab
    0.40
    চনা
    0.40
     امتحان
    0.40
    ValMap
    0.40
    綜合
    0.40
    POSITIVE LOGITS
    ب
    0.44
    Ц
    0.44
    پ
    0.43
    p
    0.43
    प
    0.40
     প
    0.39
    প
    0.39
     toprak
    0.38
    מ
    0.38
     chłop
    0.38
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.