© 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. 31-GEMMASCOPE-2-RES-262K
    7. 77405
    Prev
    Next
    INDEX
    Explanations

    structure items: lists, bullets, separators

    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
    ালা
    0.48
    鍱
    0.48
    ลอง
    0.46
    anso
    0.45
    kken
    0.45
    োর
    0.43
    ائي
    0.43
    摺
    0.43
    \|,
    0.42
     Preset
    0.42
    POSITIVE LOGITS
     nitric
    0.52
     sprint
    0.46
     bonnet
    0.45
     rng
    0.44
     iodine
    0.44
     cabins
    0.44
     cabin
    0.43
     vicar
    0.43
    perception
    0.42
     deer
    0.42
    Activations Density 0.006%

    No Known Activations