© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 99933
    Prev
    Next
    INDEX
    Explanations

    conditional logic in code or propositions

    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_262k_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
    ivă
    0.48
    ۰
    0.47
     sınır
    0.46
    用餐
    0.41
     столь
    0.41
     Puis
    0.41
    жной
    0.41
    రువు
    0.41
    rugated
    0.40
     ሂደት
    0.40
    POSITIVE LOGITS
     the
    0.54
    它是
    0.49
     there
    0.49
    &=
    0.49
     మాత్రం
    0.48
    the
    0.47
    이었
    0.46
     postoji
    0.46
     either
    0.45
    &=&
    0.45
    Activations Density 0.046%

    No Known Activations