© 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. 227083
    Prev
    Next
    INDEX
    Explanations

    formal and personal matters

    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
     बल्लेबाज
    0.49
     jat
    0.49
    哿
    0.48
     pizza
    0.47
    াচ
    0.47
     पिया
    0.46
     الناس
    0.46
     คน
    0.45
     lidí
    0.45
     snel
    0.44
    POSITIVE LOGITS
     considère
    0.52
    ISTR
    0.48
    ко
    0.47
     equatorial
    0.47
     initializes
    0.46
    ک
    0.46
    бан
    0.45
    Š
    0.44
    рио
    0.44
     appreciate
    0.44
    Activations Density 0.000%

    No Known Activations