© 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-262K
    7. 118921
    Prev
    Next
    INDEX
    Explanations

    makeup with

    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
    JECTION
    0.40
     departed
    0.40
     lighted
    0.39
    按
    0.39
    depart
    0.38
     按
    0.38
     атом
    0.38
    Departamento
    0.36
     depart
    0.36
     концер
    0.36
    POSITIVE LOGITS
    >());
    0.39
     reproducción
    0.39
    getServer
    0.38
    getWindow
    0.37
    paysys
    0.37
    在新
    0.37
     Autón
    0.36
     آه
    0.35
    uola
    0.35
    getParent
    0.35
    Activations Density 0.000%

    No Known Activations