© 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-16K
    7. 2840
    Prev
    Next
    INDEX
    Explanations

    encodes the

    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_16k_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
    மி
    0.22
     eventful
    0.21
    Usu
    0.21
     ಕೂಡ
    0.21
     للان
    0.21
    佂
    0.20
    筋肉
    0.20
    綀
    0.20
    yyyy
    0.20
     আগ্রহ
    0.20
    POSITIVE LOGITS
     the
    0.44
    the
    0.31
     teh
    0.30
     zarówno
    0.29
     các
    0.27
     ofthe
    0.26
     L
    0.26
     H
    0.26
     aceste
    0.25
     The
    0.25
    Activations Density 0.571%

    No Known Activations