© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 46705
    Prev
    Next
    INDEX
    Explanations

    static methods

    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_16_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
     Hmm
    0.57
    لون
    0.54
    匈
    0.53
    肿
    0.53
    лго
    0.51
    నూ
    0.50
    保育
    0.50
    ..");
    0.50
    ва
    0.50
     Tint
    0.50
    POSITIVE LOGITS
     voldoende
    0.63
     ince
    0.60
    as
    0.59
     academia
    0.55
     nettement
    0.54
     එක
    0.54
     précis
    0.54
     बाजार
    0.54
     allen
    0.53
     ειδ
    0.53
    Activations Density 0.001%

    No Known Activations