© 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. 41-GEMMASCOPE-2-RES-262K
    7. 31550
    Prev
    Next
    INDEX
    Explanations

    if, when, whoever, if clauses

    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_all/layer_41_width_262k_l0_big
    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
    AMENTO
    0.31
    =","><
    0.31
    oloog
    0.30
    종
    0.30
     vanwege
    0.29
    omin
    0.29
    AKE
    0.29
     operates
    0.29
     julg
    0.29
    }(\
    0.28
    POSITIVE LOGITS
     If
    0.53
    If
    0.44
     Nếu
    0.42
     ถ้า
    0.40
     Если
    0.39
     หาก
    0.39
     Whoever
    0.38
     When
    0.38
    Nếu
    0.38
     Sometimes
    0.37
    Activations Density 0.000%

    No Known Activations