© 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. 16-GEMMASCOPE-2-RES-262K
    7. 88240
    Prev
    Next
    INDEX
    Explanations

    negative numbers

    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_16_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
     Ecological
    0.59
    因
    0.58
     terhadap
    0.56
    នៃ
    0.55
     stär
    0.55
     Chiefs
    0.54
     kilometer
    0.54
     strangle
    0.54
    ，
    0.54
     Pi
    0.54
    POSITIVE LOGITS
     کنید
    0.64
    lah
    0.56
    re
    0.54
     پوش
    0.54
    entertainment
    0.54
    abı
    0.54
    iyordu
    0.53
    e
    0.53
    popularity
    0.52
     приложений
    0.52
    Activations Density 0.026%

    No Known Activations