© 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. 97587
    Prev
    Next
    INDEX
    Explanations

    foreign language terms

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

    harm anyone or yourself

    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
     furl
    0.47
    ።
    0.44
     pector
    0.43
     fanc
    0.43
     ના
    0.42
     fast
    0.41
     tapered
    0.41
     tr
    0.41
    lf
    0.41
     stå
    0.40
    POSITIVE LOGITS
    දන
    0.55
    शिक्ष
    0.53
    ্ষিকী
    0.52
    bacher
    0.50
    جراء
    0.50
    шение
    0.49
    溆
    0.49
     enseignants
    0.48
     nejen
    0.48
    老师
    0.47
    Activations Density 0.000%

    No Known Activations