© 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. 48548
    Prev
    Next
    INDEX
    Explanations

    if statement conditions

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

    If condition

    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
    प्र
    0.40
    NOVEMBER
    0.40
    팍
    0.40
    пар
    0.38
    mesinin
    0.38
    Dihydro
    0.37
    𝗱
    0.37
    陼
    0.37
     Clipboard
    0.37
     MMP
    0.37
    POSITIVE LOGITS
    ască
    0.39
     चाहें
    0.38
     είναι
    0.38
     Multiple
    0.38
     ہے
    0.38
    ulia
    0.38
     múlti
    0.37
     múltiplos
    0.37
     multiple
    0.37
    ilt
    0.37
    Activations Density 0.006%

    No Known Activations