© 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. 15242
    Prev
    Next
    INDEX
    Explanations

    industry covering

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

    refusing illegal or unethical requests

    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
    0.45
    KE
    0.41
     }^{
    0.41
    pet
    0.40
    As
    0.39
    <start_of_image>
    0.39
    ing
    0.39
    var
    0.38
     Banner
    0.38
    -
    0.38
    POSITIVE LOGITS
    णूक
    0.46
     예배
    0.46
    诓
    0.46
     consequências
    0.45
    飨
    0.45
     consecuencias
    0.44
    чами
    0.44
    相结合
    0.43
    𝐮
    0.43
     दुर्गेश
    0.43
    Activations Density 0.001%

    No Known Activations