© 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. 115496
    Prev
    Next
    INDEX
    Explanations

    aneurysm clipping

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

    fun question or one

    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
    运算
    0.54
    ్యా
    0.52
    acks
    0.50
    re
    0.49
    charts
    0.49
    挞
    0.49
    ruction
    0.48
    analyses
    0.45
    驱动
    0.45
    Axes
    0.44
    POSITIVE LOGITS
     reflet
    0.51
     esperar
    0.50
     células
    0.50
     cáps
    0.49
    線の
    0.48
     ofrecen
    0.47
     refugi
    0.46
    嘩
    0.46
     caminho
    0.46
     adaptador
    0.46
    Activations Density 0.006%

    No Known Activations