© 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. 121069
    Prev
    Next
    INDEX
    Explanations

    Follow Nicholls

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

    white pepper

    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
     cada
    0.54
    /?
    0.53
     pediat
    0.52
     informer
    0.50
     epigen
    0.49
     slayer
    0.47
     pedals
    0.47
     raspberry
    0.47
     pediatric
    0.46
     kesehatan
    0.46
    POSITIVE LOGITS
     Finished
    0.47
    啇
    0.47
    ارة
    0.46
    混凝
    0.45
     Quels
    0.45
    𝐼
    0.45
    嵐
    0.44
     Anyways
    0.44
    服
    0.44
    㗽
    0.44
    Activations Density 0.000%

    No Known Activations