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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 41281
    Prev
    Next
    INDEX
    Explanations

    used to + verb

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    i
    0.53
    doesn
    0.52
     ultimi
    0.47
     झालेले
    0.47
     перемен
    0.45
     erstes
    0.45
     erfolgte
    0.45
     условий
    0.45
     blir
    0.42
     Faraday
    0.41
    POSITIVE LOGITS
    ون
    0.62
     훨씬
    0.54
    ijan
    0.50
    že
    0.48
    eba
    0.48
     (=
    0.47
    qh
    0.47
     더
    0.46
     ބ
    0.46
    kyo
    0.45
    Activations Density 0.016%

    No Known Activations