© 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
    5. 53-GEMMASCOPE-2-RES-65K
    7. 17252
    Prev
    Next
    INDEX
    Explanations

    adjusting, adjusted, adjustable

    np_acts-logits-general · gemini-2.5-flash-lite

    adjusting clothing or appearance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_53_width_65k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    आम
    0.41
     Hj
    0.39
    আরও
    0.38
    ဖွဲ့
    0.38
    ത്ത്
    0.38
     exciting
    0.38
    禀
    0.37
    贯彻
    0.36
     glee
    0.36
     liturg
    0.36
    POSITIVE LOGITS
    commod
    0.51
    ments
    0.47
    ers
    0.44
    commodity
    0.43
     commodity
    0.42
    igations
    0.41
     Commodities
    0.41
    뻑
    0.41
    િસ્
    0.40
    ifications
    0.40
    Activations Density 0.001%

    No Known Activations