© 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. 16-GEMMASCOPE-2-RES-262K
    7. 106083
    Prev
    Next
    INDEX
    Explanations

    phrases with rather than

    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_16_width_262k_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
     Old
    0.48
     Merge
    0.48
    at
    0.47
    n
    0.46
     place
    0.42
     Jean
    0.42
     roast
    0.41
     Doo
    0.41
    y
    0.41
    AS
    0.40
    POSITIVE LOGITS
    ώς
    0.50
    মেন্ট
    0.48
    ισμού
    0.48
    ীপ
    0.47
    ಲೋ
    0.47
     financi
    0.47
    сної
    0.47
     Hadid
    0.47
    ামী
    0.46
    пенди
    0.46
    Activations Density 0.000%

    No Known Activations