© 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. 127443
    Prev
    Next
    INDEX
    Explanations

    trade, regulatory, statistics, concepts

    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
    い
    0.44
     campfire
    0.42
    2
    0.41
    Pl
    0.40
    -
    0.40
    1
    0.40
    Problem
    0.40
    Techn
    0.38
     aftermarket
    0.38
    '
    0.38
    POSITIVE LOGITS
     vuttam
    0.54
     ربنا
    0.46
     پوچھا
    0.46
    धानी
    0.46
     അദ്ദേ
    0.46
     منٹو
    0.45
     якщо
    0.45
     嗯
    0.45
     inicial
    0.45
    <unused2025>
    0.44
    Activations Density 0.008%

    No Known Activations