© 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. 196229
    Prev
    Next
    INDEX
    Explanations

    foreign scripts

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

    continued in Sudan

    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
     negligent
    0.49
     透
    0.41
     cautionary
    0.41
     Beatriz
    0.41
    륭
    0.40
    subset
    0.39
     제공
    0.39
     prévention
    0.39
     Train
    0.39
     প্রতীক
    0.39
    POSITIVE LOGITS
     कुत्तों
    0.63
    ク
    0.55
    ロ
    0.55
    य
    0.55
    ک
    0.52
    ونم
    0.52
    ति
    0.52
    ولی
    0.52
    گوید
    0.52
    к
    0.52
    Activations Density 0.000%

    No Known Activations