© 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. 148441
    Prev
    Next
    INDEX
    Explanations

    portfolio of research

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

    financial accounts and services

    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
     ਦਾ
    0.48
     dahulu
    0.46
    že
    0.45
    मुख
    0.44
    琀
    0.43
    зви
    0.43
    酥
    0.43
    萸
    0.42
     aanwezig
    0.41
     clearContext
    0.41
    POSITIVE LOGITS
     bạn
    0.51
     Sicher
    0.47
     Fant
    0.47
     Bewert
    0.46
     الاك
    0.46
    perform
    0.45
    nano
    0.45
    for
    0.44
     Sperm
    0.44
     φορ
    0.44
    Activations Density 0.000%

    No Known Activations