© 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-262K
    7. 201648
    Prev
    Next
    INDEX
    Explanations

    account name

    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_262k_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
    ib
    0.51
     تكونوا
    0.48
    csv
    0.46
     الاسئله
    0.46
    obj
    0.43
    icletas
    0.42
    hidrat
    0.42
    犾
    0.42
    nag
    0.42
    pretty
    0.42
    POSITIVE LOGITS
    она
    0.53
     largura
    0.48
     enfon
    0.48
     luces
    0.48
     encomenda
    0.47
     weiter
    0.46
    UIL
    0.45
     speł
    0.45
     pendiente
    0.45
     offenbar
    0.45
    Activations Density 0.002%

    No Known Activations