© 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-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 62684
    Prev
    Next
    INDEX
    Explanations

    checking accounts or savings accounts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     crippled
    0.46
    を開始
    0.41
     фильма
    0.40
     дуже
    0.40
    肋
    0.40
     ходить
    0.39
    unstyled
    0.39
     Chayin
    0.38
     квар
    0.37
     crab
    0.37
    POSITIVE LOGITS
     ions
    0.44
    cionario
    0.44
    ق
    0.43
    াসী
    0.42
    ધાનસભા
    0.42
    FromBody
    0.41
    ﻤ
    0.40
     kor
    0.39
     seterusnya
    0.39
    ังกฤษ
    0.39
    Activations Density 0.001%

    No Known Activations