© 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. 43987
    Prev
    Next
    INDEX
    Explanations

    negative condition descriptions

    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
    USE
    0.44
     narod
    0.44
    は大
    0.42
     glutamate
    0.40
     রোনাল
    0.40
     trưởng
    0.40
    鍑
    0.39
    瞬间
    0.39
     monop
    0.39
     hardware
    0.39
    POSITIVE LOGITS
    ak
    0.53
     zaidi
    0.45
     Казахстан
    0.44
    il
    0.43
    supers
    0.42
     youre
    0.42
    elten
    0.42
    your
    0.41
    akre
    0.41
     /\.
    0.41
    Activations Density 0.002%

    No Known Activations