© 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
    5. 31-GEMMASCOPE-2-RES-16K
    7. 14334
    Prev
    Next
    INDEX
    Explanations

    SAS expander

    np_acts-logits-general · gemini-2.5-flash-lite

    listing components and attributes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     мла
    0.45
     이러
    0.42
    或其他
    0.41
     СА
    0.39
     بسر
    0.38
     органи
    0.38
     얻
    0.38
     několika
    0.37
    𝐞
    0.37
     אבל
    0.36
    POSITIVE LOGITS
    側の
    0.51
    gate
    0.45
     phase
    0.42
    phase
    0.41
    ുകൊണ്ട്
    0.41
    িগণ
    0.40
     centric
    0.40
    懺
    0.39
     மற்றும்
    0.39
     Phần
    0.39
    Activations Density 0.694%

    No Known Activations