© 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. 46504
    Prev
    Next
    INDEX
    Explanations

    previous knowledge or items

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

    iced tea, extra strong, animal digestion

    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
     Kardash
    0.47
     generan
    0.47
     impair
    0.45
    ედერ
    0.45
     вследствие
    0.44
     конку
    0.44
    अधिकांश
    0.44
    譏
    0.43
     stargazerCount
    0.43
     Aleksandar
    0.42
    POSITIVE LOGITS
    或是
    0.56
     veggies
    0.55
     you
    0.55
     bạn
    0.54
    jar
    0.53
     oder
    0.52
     或者
    0.52
    you
    0.52
    里面
    0.52
     ơi
    0.52
    Activations Density 0.000%

    No Known Activations