© 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. 40-GEMMASCOPE-2-RES-262K
    7. 166517
    Prev
    Next
    INDEX
    Explanations

    extremists, extremism, sharp objects

    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
     visually
    0.39
     classically
    0.39
    玛
    0.39
     cliff
    0.38
    cliff
    0.38
     seinem
    0.37
    ')
    0.37
     visual
    0.37
    brook
    0.37
    ']}
    0.36
    POSITIVE LOGITS
     extremists
    0.53
     extremist
    0.47
    สุด
    0.46
     extremism
    0.46
     extremity
    0.45
    頭髮
    0.43
    extrem
    0.42
     ########.
    0.42
     ekstrem
    0.42
    體的
    0.41
    Activations Density 0.000%

    No Known Activations