© 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. 40-GEMMASCOPE-2-RES-262K
    7. 10588
    Prev
    Next
    INDEX
    Explanations

    counts of unique items

    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_40_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
     ciertas
    0.44
     néhány
    0.42
    Guesses
    0.41
     infrastrukt
    0.41
     escuchar
    0.39
     nekoliko
    0.38
     কয়েকজন
    0.38
    掊
    0.38
    خی
    0.38
     några
    0.38
    POSITIVE LOGITS
     different
    0.66
    different
    0.64
    不同的
    0.62
     unique
    0.59
    unique
    0.58
     வகையான
    0.56
     individual
    0.53
     (!)
    0.53
    不同
    0.49
     distinct
    0.49
    Activations Density 0.019%

    No Known Activations