© 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. 24782
    Prev
    Next
    INDEX
    Explanations

    inscribe data

    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
    ű
    0.59
    üne
    0.54
    adoc
    0.49
    ikir
    0.48
    覬
    0.48
    ansen
    0.48
    кра
    0.47
    אר
    0.47
    әм
    0.47
    ilik
    0.46
    POSITIVE LOGITS
    ു
    0.50
     (=
    0.46
     وبال
    0.42
    ಪಡ
    0.41
    Tel
    0.40
     entraî
    0.40
     gels
    0.39
    Milliseconds
    0.39
     Aye
    0.39
    tib
    0.39
    Activations Density 0.003%

    No Known Activations