© 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. 150432
    Prev
    Next
    INDEX
    Explanations

    payment, invoice, or jeopardy

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

    non-english characters and common english words

    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
    ಾದರೆ
    0.50
    挕
    0.46
    ни
    0.46
    nti
    0.43
    ikkh
    0.43
    माइंडर
    0.42
    isiaj
    0.42
    halogen
    0.42
     বিপ্লবী
    0.42
    VK
    0.41
    POSITIVE LOGITS
    Ж
    0.49
     Navarre
    0.47
    ยาว
    0.46
    ുന്ന
    0.44
    うまく
    0.43
     باك
    0.42
     Elinor
    0.41
    當年
    0.41
     Gert
    0.40
    至今
    0.40
    Activations Density 0.002%

    No Known Activations