© 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-65K
    7. 65506
    Prev
    Next
    INDEX
    Explanations

    options, model, Name, buy

    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_65k_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
    ADOC
    0.42
    <unused238>
    0.41
     як
    0.41
    數據
    0.41
     ಕ್ರ
    0.41
     محاضره
    0.40
    Bismillahirrah
    0.40
    总部
    0.39
    IANA
    0.39
    紀
    0.38
    POSITIVE LOGITS
     Paste
    0.40
    Stencil
    0.39
     rental
    0.38
     hostess
    0.38
     injection
    0.38
     label
    0.37
     gradient
    0.37
     bunch
    0.37
     پہلی
    0.37
    レンタル
    0.37
    Activations Density 0.002%

    No Known Activations