© 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. 5816
    Prev
    Next
    INDEX
    Explanations

    emphasis after a comma

    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
     {//
    0.54
    ొక్క
    0.50
    UMPS
    0.50
     semper
    0.49
     gummy
    0.49
    ឹក
    0.47
     ecosystems
    0.46
     turbines
    0.46
     /(
    0.46
     whose
    0.46
    POSITIVE LOGITS
     If
    0.63
    án
    0.58
    ando
    0.57
    ica
    0.50
    If
    0.50
     Inoltre
    0.50
     Additionally
    0.50
    ui
    0.48
     In
    0.48
     Unlike
    0.48
    Activations Density 0.031%

    No Known Activations