© 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. 203460
    Prev
    Next
    INDEX
    Explanations

    reduction, APIs, numbers, meltdown

    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
    ный
    0.52
    的时
    0.50
     NIV
    0.47
    Tool
    0.47
    咟
    0.46
     Vest
    0.46
    Vest
    0.45
    Romantic
    0.45
    的时间
    0.44
    DIS
    0.44
    POSITIVE LOGITS
     firepower
    0.50
     neighborhoods
    0.47
     pharmacies
    0.45
     neighbourhoods
    0.44
    e
    0.44
     woes
    0.43
    òu
    0.43
     toxins
    0.43
    re
    0.42
     maa
    0.42
    Activations Density 0.001%

    No Known Activations