© 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. 40-GEMMASCOPE-2-RES-65K
    7. 514
    Prev
    Next
    INDEX
    Explanations

    how to use

    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_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
    r
    0.30
    тері
    0.29
    aturi
    0.29
    strup
    0.28
    lių
    0.28
    ।
    0.27
    ignée
    0.27
    teri
    0.26
    役割
    0.26
    ヴ
    0.26
    POSITIVE LOGITS
     techniques
    0.54
     técnicas
    0.46
     tecniche
    0.45
    fully
    0.42
     methods
    0.41
     sparingly
    0.40
     leverage
    0.40
     hindsight
    0.39
     метода
    0.39
     interchangeably
    0.39
    Activations Density 0.386%

    No Known Activations