© 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. 144988
    Prev
    Next
    INDEX
    Explanations

    descriptive or elaborative continuations

    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
     Ար
    0.57
    ี
    0.57
     a
    0.57
     Полу
    0.55
    r
    0.53
    ys
    0.52
     szkoły
    0.52
    끗
    0.52
     Πα
    0.51
     عالی
    0.51
    POSITIVE LOGITS
     delect
    0.50
     inaction
    0.50
    عي
    0.49
     agreements
    0.47
     incum
    0.47
     newspap
    0.47
    淖
    0.47
    原始内容
    0.46
    teeth
    0.46
     MacArthur
    0.46
    Activations Density 0.000%

    No Known Activations