© 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. 199705
    Prev
    Next
    INDEX
    Explanations

    harmful criticism and blame

    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
    u
    0.50
     नामा
    0.46
    اسية
    0.46
    ంపు
    0.44
    p
    0.42
    h
    0.41
    zach
    0.41
     svenska
    0.41
     ಆನಿ
    0.41
    طلع
    0.40
    POSITIVE LOGITS
     criticism
    0.47
     criticize
    0.47
     Duc
    0.43
     promote
    0.43
    ড়যন্ত্র
    0.42
     blame
    0.42
     unfounded
    0.41
     συγκεκρι
    0.41
     complained
    0.40
    鏝
    0.40
    Activations Density 0.002%

    No Known Activations