© 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. 10774
    Prev
    Next
    INDEX
    Explanations

    Body Art / Adornment

    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
    ंटे
    0.49
    DanhMucSP
    0.45
    hereinafter
    0.45
    ില
    0.45
    elevationMap
    0.44
    kjhtml
    0.44
    rono
    0.44
    ཋ
    0.44
    MaxIntensity
    0.43
    buttonLevel
    0.43
    POSITIVE LOGITS
     Legal
    0.64
     Cultures
    0.51
     Projekte
    0.50
     Moral
    0.50
    0.50
     Culture
    0.49
     Correct
    0.48
     when
    0.48
    n
    0.48
     UK
    0.47
    Activations Density 0.049%

    No Known Activations