© 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. 31-GEMMASCOPE-2-RES-262K
    7. 17405
    Prev
    Next
    INDEX
    Explanations

    how things are

    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
     نړۍ
    0.45
     pienso
    0.45
     quero
    0.45
     söyle
    0.44
    (@"
    0.43
     discont
    0.42
    ක
    0.42
     anden
    0.41
     mesmas
    0.41
    ارين
    0.41
    POSITIVE LOGITS
     উৎপত্তি
    0.47
     Anc
    0.44
    στηκε
    0.44
     беше
    0.43
     전류
    0.40
     знай
    0.40
    താണ്
    0.40
     Generating
    0.40
    </h2>
    0.39
    ρευ
    0.39
    Activations Density 0.005%

    No Known Activations