© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 61443
    Prev
    Next
    INDEX
    Explanations

    conditional statements (if/then)

    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
    ก็จะ
    0.50
    will
    0.48
    na
    0.44
    ane
    0.43
    会不会
    0.43
     будет
    0.42
     خواهد
    0.42
    à
    0.41
    anye
    0.41
     will
    0.40
    POSITIVE LOGITS
     તમે
    0.56
     आपने
    0.54
     jste
    0.54
     vostri
    0.52
     avete
    0.51
    あなたが
    0.50
     bạn
    0.49
     votre
    0.49
     imate
    0.49
    คุณ
    0.48
    Activations Density 0.000%

    No Known Activations