© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 172409
    Prev
    Next
    INDEX
    Explanations

    styles and actions

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

    scammer deceiving lies

    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_262k_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
    淋
    0.49
     ἢ
    0.47
     peralatan
    0.46
     помощ
    0.46
     aute
    0.46
    न्स
    0.45
     alasan
    0.45
     teaser
    0.45
     potensi
    0.45
     दिलचस्पी
    0.45
    POSITIVE LOGITS
    imagens
    0.49
    âni
    0.47
    🕉
    0.46
     obtenir
    0.45
    🙏
    0.44
    𓂀
    0.44
     🙏
    0.42
     resumed
    0.42
    形成的
    0.42
    传
    0.42
    Activations Density 0.000%

    No Known Activations