© 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. 224934
    Prev
    Next
    INDEX
    Explanations

    avoiding certain types of questions

    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
     annihilated
    0.45
    %,
    0.41
    䚰
    0.41
    ರವಾಗಿ
    0.40
     入り
    0.39
    मर्द
    0.38
    iyas
    0.38
    iyam
    0.37
     ಧ
    0.37
    ][%
    0.37
    POSITIVE LOGITS
     Upper
    0.44
     నె
    0.42
     Cocoa
    0.42
     planters
    0.40
    ปรับ
    0.37
     planter
    0.37
     upper
    0.35
     ప్రశ్
    0.35
     Hospice
    0.35
     Lower
    0.35
    Activations Density 0.002%

    No Known Activations