© 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. 120734
    Prev
    Next
    INDEX
    Explanations

    best place

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

    selecting entire data range

    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
    s
    0.57
    as
    0.54
    es
    0.54
    ים
    0.54
    ی
    0.48
    u
    0.48
    aq
    0.47
    etext
    0.46
    ా
    0.45
    ا
    0.45
    POSITIVE LOGITS
     নিয়ন্ত্রণ
    0.52
    ędzynarod
    0.51
    𝒕
    0.51
     игроков
    0.50
    ट्स
    0.50
     உதவி
    0.50
     невозможно
    0.49
     التحكم
    0.48
     अवै
    0.48
     নিয়ন্ত্রণ
    0.48
    Activations Density 0.000%

    No Known Activations