© 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-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 23872
    Prev
    Next
    INDEX
    Explanations

    killed

    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_40_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
     alguém
    0.46
     suicidal
    0.43
    బో
    0.40
     unfortunate
    0.39
    ាស់
    0.38
     provoqu
    0.38
    İK
    0.37
    濺
    0.37
    uation
    0.37
    র্ঘট
    0.37
    POSITIVE LOGITS
     menerapkan
    0.41
     във
    0.38
    iper
    0.38
    ក្នុងការ
    0.38
    எஸ்
    0.37
     në
    0.37
     ઉપરાંત
    0.37
    ϛ
    0.37
     V
    0.37
     mewn
    0.37
    Activations Density 0.002%

    No Known Activations