© 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. 31-GEMMASCOPE-2-RES-16K
    7. 5653
    Prev
    Next
    INDEX
    Explanations

    measurements and ingredients

    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
     descrito
    0.46
     permettre
    0.42
     умер
    0.41
     falleció
    0.39
    夭
    0.39
     postpon
    0.39
     विरोध
    0.38
    ئين
    0.37
    誹
    0.37
    ifon
    0.37
    POSITIVE LOGITS
     advisor
    0.43
     adviser
    0.39
    اعات
    0.39
    াতি
    0.37
     راست
    0.37
     consultant
    0.37
     सलाहकार
    0.36
     книги
    0.36
     Technically
    0.36
     ...)
    0.35
    Activations Density 0.016%

    No Known Activations