© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 241733
    Prev
    Next
    INDEX
    Explanations

    arrival, reasons, expenses, credit

    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
     особли
    0.50
     اصحاب
    0.49
     социальных
    0.49
     heureux
    0.49
     risultato
    0.48
     especiais
    0.48
     သည်
    0.48
    䏹
    0.47
     anggota
    0.46
     அம்ம
    0.45
    POSITIVE LOGITS
    u
    0.48
    backing
    0.47
     backing
    0.46
     linen
    0.45
    Prox
    0.45
    Squ
    0.45
    wavelength
    0.45
    ার্চ
    0.45
    ULL
    0.44
    PP
    0.44
    Activations Density 0.000%

    No Known Activations