© 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. 16-GEMMASCOPE-2-RES-262K
    7. 6475
    Prev
    Next
    INDEX
    Explanations

    can't help but

    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_16_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
     ]]
    0.71
     Doesn
    0.70
     besitzt
    0.70
     niemals
    0.69
     மட்டுமே
    0.68
    ки
    0.68
    jones
    0.66
     jederzeit
    0.63
     quelcon
    0.63
    écies
    0.63
    POSITIVE LOGITS
    s
    0.83
     on
    0.68
    <0xBF>
    0.67
    ス
    0.64
    当
    0.63
    ﻨ
    0.62
    る
    0.62
     surprising
    0.61
     wonder
    0.61
    d
    0.59
    Activations Density 0.007%

    No Known Activations