© 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. 222685
    Prev
    Next
    INDEX
    Explanations

    Steel Panther and Florida

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

    package manager or OS parts

    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
    ﾎ
    0.58
     tabla
    0.50
    胡
    0.50
     maquinaria
    0.49
    借
    0.49
    tabla
    0.48
    抵
    0.48
    懸
    0.47
     noção
    0.46
    乞
    0.46
    POSITIVE LOGITS
    ian
    0.49
    ie
    0.48
     IRL
    0.48
           
    0.47
     epis
    0.47
     RD
    0.47
     affiliations
    0.46
     وغیرہ
    0.46
     etc
    0.46
     GI
    0.45
    Activations Density 0.002%

    No Known Activations