© 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-3-4B-IT
    5. 29-GEMMASCOPE-2-RES-65K
    7. 5007
    Prev
    Next
    INDEX
    Explanations

    avoiding negative qualities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_29_width_65k_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
     pł
    0.73
     calma
    0.72
     淡
    0.70
    平静
    0.67
    穏
    0.66
    認
    0.62
     cleanse
    0.62
     순
    0.62
    stav
    0.62
     片
    0.61
    POSITIVE LOGITS
     bulky
    1.48
     uncomfortable
    1.45
     cumbersome
    1.41
     restrictive
    1.38
     bulk
    1.35
     restricting
    1.22
     unsightly
    1.21
    Bulk
    1.20
     awkward
    1.20
    bulk
    1.19
    Activations Density 0.180%

    No Known Activations