© 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. 66618
    Prev
    Next
    INDEX
    Explanations

    predictive conditional statements

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

    conditional statements

    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
     грузо
    0.45
     skór
    0.44
     zum
    0.44
     puts
    0.43
    n
    0.43
     khối
    0.42
     bě
    0.41
    t
    0.41
     delivers
    0.40
     Là
    0.40
    POSITIVE LOGITS
    pubescens
    0.62
    यदि
    0.56
    если
    0.49
    Recommendations
    0.49
     अगर
    0.48
     Если
    0.48
    ถ้า
    0.48
    Если
    0.47
     إذا
    0.46
     eğer
    0.46
    Activations Density 0.003%

    No Known Activations