© 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. 13306
    Prev
    Next
    INDEX
    Explanations

    choice or option

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

    offers choices or options

    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
    赧
    0.53
    あの
    0.52
    despite
    0.50
    Ironically
    0.50
     misguided
    0.49
     unjust
    0.48
    헌
    0.48
    ጣም
    0.48
     pernicious
    0.47
     आतंकवाद
    0.47
    POSITIVE LOGITS
     either
    0.77
     entweder
    0.74
     выбран
    0.70
     chosen
    0.68
     escolh
    0.66
    要么
    0.66
     optional
    0.64
     preferably
    0.64
     либо
    0.60
    或者是
    0.59
    Activations Density 0.045%

    No Known Activations