© 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. 27981
    Prev
    Next
    INDEX
    Explanations

    a collaboration or vote

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

    adjusting specific potentials

    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
     Deze
    0.52
     by
    0.51
    Deze
    0.49
     or
    0.48
     aby
    0.47
     मोठा
    0.47
    ਗ
    0.47
    by
    0.46
     with
    0.46
     मोठे
    0.46
    POSITIVE LOGITS
    蕤
    0.46
    窑
    0.46
     शायद
    0.45
    蜞
    0.45
    锆
    0.45
     সম্ভবত
    0.44
    询问
    0.44
    泷
    0.44
    صیلی
    0.43
     olmadığını
    0.43
    Activations Density 0.001%

    No Known Activations