© 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. 127408
    Prev
    Next
    INDEX
    Explanations

    niches, Wireless, office, Finance

    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
     cigars
    0.54
     автомобиля
    0.53
     হোমিওপ্যাথির
    0.52
    𝐣
    0.52
    າມ
    0.50
     conceived
    0.50
    💿
    0.50
    норийска
    0.50
    сцю
    0.50
    გუფი
    0.50
    POSITIVE LOGITS
    0.65
     '
    0.52
    л
    0.52
     The
    0.51
     Evolution
    0.47
     TH
    0.46
    ל
    0.46
     B
    0.44
     Grand
    0.44
     F
    0.43
    Activations Density 0.003%

    No Known Activations