© 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. 31-GEMMASCOPE-2-RES-262K
    7. 53821
    Prev
    Next
    INDEX
    Explanations

    app features and descriptions

    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
     debemos
    0.55
     devemos
    0.55
    𝘐
    0.54
    Ли
    0.52
     élev
    0.49
     сигна
    0.48
    𝖓
    0.47
     humild
    0.47
    ᇁ
    0.47
    Би
    0.47
    POSITIVE LOGITS
     Gro
    0.44
    get
    0.43
     quote
    0.42
     Android
    0.41
     flip
    0.41
     confluence
    0.40
     separate
    0.40
    ge
    0.40
    gear
    0.39
     certain
    0.39
    Activations Density 0.003%

    No Known Activations