© 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. 67192
    Prev
    Next
    INDEX
    Explanations

    multilingual specific scripts

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

    steal credentials

    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
     scoot
    0.51
     visits
    0.50
     Dose
    0.49
     verse
    0.49
     be
    0.48
     Visits
    0.47
    }=-\
    0.47
     worsen
    0.47
     scored
    0.46
     perror
    0.46
    POSITIVE LOGITS
    ுடைய
    0.55
    Ná
    0.54
    Người
    0.52
     اسرائی
    0.51
    牖
    0.51
    razione
    0.51
     ایسی
    0.51
    懒
    0.50
    짧
    0.49
    জি
    0.49
    Activations Density 0.000%

    No Known Activations