© 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-TRANSCODER-262K
    7. 80698
    Prev
    Next
    INDEX
    Explanations

    Ukrainian history and politics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_31_width_262k_l0_small_affine
    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
    Efter
    0.43
    Ἠ
    0.41
     ఆధ్యా
    0.41
    Below
    0.39
    Луч
    0.39
    iata
    0.38
    aksud
    0.38
     రావ
    0.38
    anski
    0.37
    Imagine
    0.37
    POSITIVE LOGITS
     whitening
    0.41
     crema
    0.38
     bol
    0.37
     бол
    0.37
    وزيع
    0.36
     Bol
    0.36
    複
    0.36
     freepik
    0.35
     Junta
    0.35
     double
    0.35
    Activations Density 0.030%

    No Known Activations