© 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. 40-GEMMASCOPE-2-RES-262K
    7. 11773
    Prev
    Next
    INDEX
    Explanations

    bottom line, bottom-up, bottomless

    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
     Consultancy
    0.44
     Scientist
    0.42
     normativa
    0.41
    忔
    0.40
    يه
    0.39
     vü
    0.39
     Conditioner
    0.39
     Combo
    0.39
    の高い
    0.38
     remanded
    0.38
    POSITIVE LOGITS
     bottom
    0.73
    Bottom
    0.73
    bottom
    0.69
     Bottom
    0.67
     đáy
    0.67
    底
    0.66
     bottoms
    0.64
    底部
    0.64
     底
    0.49
    BOTTOM
    0.49
    Activations Density 0.009%

    No Known Activations