© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 79890
    Prev
    Next
    INDEX
    Explanations

    landing page direct

    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
     considerado
    0.47
     चर्चित
    0.45
     الف
    0.45
    ificare
    0.43
    izarea
    0.43
     виконання
    0.43
    佞
    0.43
     considerato
    0.41
    م
    0.41
     carácter
    0.41
    POSITIVE LOGITS
     simpler
    0.43
     easier
    0.42
     pediat
    0.42
     এতে
    0.41
     wsi
    0.41
     safer
    0.40
    Gosudarstvennyj
    0.40
    '
    0.40
     Easier
    0.39
     liners
    0.38
    Activations Density 0.003%

    No Known Activations