© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 2715
    Prev
    Next
    INDEX
    Explanations

    / currencies or block currencies

    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_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
    ProjectReference
    0.40
    ="#"><
    0.38
    庆祝
    0.38
    OutputFile
    0.38
    modelVersion
    0.38
     trypsin
    0.37
    圤
    0.37
    icillium
    0.37
    гти
    0.36
     মুক্তিবাহিনীর
    0.35
    POSITIVE LOGITS
     ID
    0.40
    RELATED
    0.36
     cara
    0.35
     sm
    0.34
    incinnati
    0.34
     mar
    0.34
     giant
    0.34
    FIVE
    0.33
     bur
    0.32
     n
    0.32
    Activations Density 0.002%

    No Known Activations