© 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. 48864
    Prev
    Next
    INDEX
    Explanations

    ifdef conditional compilation

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

    conditional statements `if`, `whether`

    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
    手指
    0.41
    moto
    0.41
     Ribeiro
    0.40
     Pérez
    0.39
    CHD
    0.38
     Mainly
    0.38
    潁
    0.38
    Vill
    0.38
    蝰
    0.38
     Villas
    0.37
    POSITIVE LOGITS
     unimplemented
    0.43
     constituer
    0.43
     constitue
    0.40
    DefineConstants
    0.39
     bool
    0.39
     conditional
    0.38
     environ
    0.38
     Denmark
    0.38
     discard
    0.38
     whiche
    0.37
    Activations Density 0.000%

    No Known Activations