© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 138488
    Prev
    Next
    INDEX
    Explanations

    negation after probability or certainty

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_37_width_262k_l0_small_affine
    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
    мп
    0.41
     Sdn
    0.40
    Supply
    0.38
    ﴾
    0.38
     nothing
    0.37
    une
    0.37
     silico
    0.37
    ؒ
    0.36
     supply
    0.35
    mp
    0.35
    POSITIVE LOGITS
    सै
    0.38
    વામાં
    0.37
    Doming
    0.36
    стары
    0.35
    िमा
    0.35
     Fabian
    0.34
    าท
    0.34
    सीमा
    0.34
    吲
    0.34
    Наи
    0.33
    Activations Density 0.050%

    No Known Activations