© 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. 35449
    Prev
    Next
    INDEX
    Explanations

    available to

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

    availability and interfaces

    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
     Kenya
    0.52
     ܐ
    0.50
     Mombasa
    0.49
     பாம்ப
    0.48
     Oceania
    0.48
     Ξ
    0.48
     Rohingya
    0.48
     ブル
    0.47
     Galapagos
    0.47
     รู้
    0.46
    POSITIVE LOGITS
     realizan
    0.47
    此次
    0.45
    大型
    0.44
    Formal
    0.42
    تد
    0.42
     aumenta
    0.42
    M
    0.41
    大多
    0.41
    ordinal
    0.41
     talaga
    0.41
    Activations Density 0.000%

    No Known Activations