© 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. 31-GEMMASCOPE-2-RES-262K
    7. 11648
    Prev
    Next
    INDEX
    Explanations

    understand your approach

    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_31_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
     that
    0.46
    uset
    0.46
    that
    0.46
    owner
    0.46
     hundred
    0.45
    ].[
    0.44
     If
    0.43
    op
    0.42
    티
    0.42
    🎷
    0.42
    POSITIVE LOGITS
     accumulates
    0.49
     台
    0.49
     convivencia
    0.49
     показателей
    0.46
    ຢ່າງ
    0.45
    ອບ
    0.43
     indoct
    0.41
    Չ
    0.41
    ່າຍ
    0.41
     संकट
    0.40
    Activations Density 0.001%

    No Known Activations