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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 11482
    Prev
    Next
    INDEX
    Explanations

    hell and hellish concepts

    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_16_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
    é
    1.45
    y
    1.38
    т
    1.36
    и
    1.32
    ле
    1.30
    il
    1.29
    л
    1.29
    z
    1.27
    ي
    1.25
    ни
    1.21
    POSITIVE LOGITS
     hell
    1.19
     Hell
    1.00
    Hell
    0.91
     heavens
    0.91
     pilgrimage
    0.86
    hell
    0.82
    獄
    0.81
     troop
    0.81
    0.79
     realms
    0.77
    Activations Density 0.011%

    No Known Activations