© 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. 70816
    Prev
    Next
    INDEX
    Explanations

    years that

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

    avoiding explicit content

    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
     বৌদ্ধ
    0.46
    ོད་
    0.46
     sexist
    0.43
    ন্ত্রী
    0.42
     বিদেশ
    0.42
    hotels
    0.42
    蕉
    0.42
     motel
    0.42
     intercultural
    0.41
     syukur
    0.41
    POSITIVE LOGITS
     лов
    0.42
     walks
    0.41
    会
    0.41
     إن
    0.40
    依然
    0.40
     infestations
    0.39
     каран
    0.39
    绰
    0.39
    正常
    0.38
    账
    0.38
    Activations Density 0.001%

    No Known Activations