© 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-3-1B-IT
    5. 13-GEMMASCOPE-2-RES-16K
    7. 4775
    Prev
    Next
    INDEX
    Explanations

    `if` conditions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_13_width_16k_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
     composición
    1.23
     composição
    1.04
     kadın
    1.00
     Tamaño
    0.98
    RawContext
    0.97
    婄
    0.96
     arred
    0.95
     últimas
    0.93
    捎
    0.93
     cognitiva
    0.92
    POSITIVE LOGITS
     IN
    0.76
     Institute
    0.73
     ins
    0.72
     INS
    0.69
     IF
    0.69
     In
    0.68
     Earn
    0.68
    inspect
    0.64
    •
    0.64
    ↵↵
    0.62
    Activations Density 0.016%

    No Known Activations