© 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. 210822
    Prev
    Next
    INDEX
    Explanations

    actions followed by to or when

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

    benefits, statistics, and spam

    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
    ells
    0.50
    湟
    0.49
     സംഘടന
    0.48
     ہوتے
    0.47
     নিশ্চয়
    0.47
    enaire
    0.46
     عايزين
    0.46
    Conta
    0.45
    anks
    0.45
     دیتے
    0.45
    POSITIVE LOGITS
    '
    0.55
    י
    0.52
     марта
    0.48
     zucchini
    0.46
     hémorro
    0.45
     zvyš
    0.45
    จาก
    0.44
     reprogram
    0.44
    Figure
    0.43
     theres
    0.43
    Activations Density 0.001%

    No Known Activations