© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 57550
    Prev
    Next
    INDEX
    Explanations

    discussing sensitive topics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     consumed
    0.41
    业
    0.41
     intersected
    0.39
     incidentally
    0.38
     nằm
    0.37
     grazed
    0.37
    ﺧ
    0.37
     unterwegs
    0.37
     saved
    0.37
    業
    0.37
    POSITIVE LOGITS
    randomNumber
    0.43
    cience
    0.42
     intenso
    0.40
    illante
    0.39
     intensive
    0.38
    applying
    0.38
     muit
    0.38
    砊
    0.38
    #'
    0.38
    𝚎
    0.38
    Activations Density 0.001%

    No Known Activations