© 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-IT
    5. 40-GEMMASCOPE-2-RES-65K
    7. 3422
    Prev
    Next
    INDEX
    Explanations

    `if` and `while` statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_65k_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
     É
    0.38
     በአ
    0.35
     ass
    0.34
    आ
    0.33
    默
    0.33
     Á
    0.33
     ordre
    0.33
    距離
    0.32
    ودي
    0.32
     ভুল
    0.32
    POSITIVE LOGITS
     clauses
    0.60
     clause
    0.60
    语句
    0.58
    clause
    0.52
     statements
    0.51
    ___
    0.51
     Statements
    0.50
    statement
    0.49
     Clauses
    0.49
    statements
    0.49
    Activations Density 0.264%

    No Known Activations