© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 52068
    Prev
    Next
    INDEX
    Explanations

    stating facts or conditions

    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
     આપણા
    0.49
     अफगानिस्तान
    0.46
    GA
    0.46
     алгорит
    0.45
    実装
    0.45
    解析
    0.44
    咛
    0.44
     algorithm
    0.43
    }_{\
    0.43
     nieuw
    0.43
    POSITIVE LOGITS
    dirt
    0.48
     turpentine
    0.44
    dice
    0.43
    slice
    0.43
    க்கர
    0.41
     cintura
    0.41
    damaged
    0.40
    each
    0.40
    endre
    0.40
    牽
    0.40
    Activations Density 0.003%

    No Known Activations