© 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. 8153
    Prev
    Next
    INDEX
    Explanations

    application settings and menus

    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
     imprecise
    0.45
     excessively
    0.41
     ఉ
    0.39
     contaba
    0.38
     overly
    0.38
    发布
    0.37
    RawContext
    0.37
    Ƭ
    0.37
    ֡
    0.36
     showcased
    0.36
    POSITIVE LOGITS
     seguir
    0.47
    agree
    0.47
    change
    0.46
     penc
    0.46
    approval
    0.45
    adi
    0.44
    outlook
    0.44
    clicked
    0.44
    utus
    0.43
    endre
    0.42
    Activations Density 0.016%

    No Known Activations