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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 44063
    Prev
    Next
    INDEX
    Explanations

    — enhancing beauty

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

    light bulb jokes

    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_31_width_262k_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
     veer
    0.44
    职
    0.43
    뻣
    0.43
     تبدیلی
    0.40
     inbuilt
    0.40
     पहिले
    0.39
    erkt
    0.38
     pin
    0.38
     ዘ
    0.38
    Couple
    0.38
    POSITIVE LOGITS
     reiterated
    0.46
     Neutron
    0.42
     Figur
    0.41
     AVE
    0.40
    ানী
    0.40
     Symphony
    0.39
    RICAL
    0.39
    \}.
    0.39
    новен
    0.38
     Cardano
    0.38
    Activations Density 0.000%

    No Known Activations