© 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. 13564
    Prev
    Next
    INDEX
    Explanations

    evaluating if conditions

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

    conditional logic and programming control flow

    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
    ทะ
    0.52
    襲
    0.48
    憧
    0.48
    妝
    0.47
    絨
    0.47
    キャ
    0.46
     отда
    0.45
    記念
    0.44
    職
    0.44
    Paf
    0.44
    POSITIVE LOGITS
     조건
    0.79
     condition
    0.78
    条件
    0.78
     Conditions
    0.77
     condizione
    0.77
     Boolean
    0.77
     conditions
    0.76
     conditionals
    0.75
     conditional
    0.73
    Boolean
    0.71
    Activations Density 0.020%

    No Known Activations