© 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. 224131
    Prev
    Next
    INDEX
    Explanations

    instructions and situations

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

    Developed, pronged, Standalone

    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
    седа
    0.49
     locom
    0.47
     plata
    0.47
    куру
    0.46
    y
    0.44
    及び
    0.43
    の話
    0.43
     եւ
    0.43
    かも
    0.43
     beheld
    0.42
    POSITIVE LOGITS
    ل
    0.54
     આપે
    0.49
    lös
    0.48
    Give
    0.46
     దర్శక
    0.44
     fáb
    0.44
    Thankfully
    0.44
    वैसे
    0.44
     schop
    0.44
    痱
    0.44
    Activations Density 0.002%

    No Known Activations