© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 21689
    Prev
    Next
    INDEX
    Explanations

    xml namespaces

    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_40_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
     रुपया
    0.41
    ಿತ
    0.39
     Опера
    0.39
    इससे
    0.38
    ocsát
    0.38
     ocurrir
    0.38
    ༨
    0.38
    ">';
    0.37
    គាត់
    0.37
    僌
    0.37
    POSITIVE LOGITS
     stays
    0.40
     كل
    0.38
     VMs
    0.37
    IKI
    0.36
     amm
    0.36
    бр
    0.35
    fluence
    0.35
    stays
    0.34
    ান্তরে
    0.34
    тно
    0.34
    Activations Density 0.000%

    No Known Activations