© 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. 31-GEMMASCOPE-2-RES-262K
    7. 75684
    Prev
    Next
    INDEX
    Explanations

    poly prefix

    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
    a
    0.66
    ra
    0.62
    le
    0.59
    y
    0.57
    ste
    0.55
    la
    0.53
    es
    0.52
    to
    0.52
    g
    0.52
    li
    0.52
    POSITIVE LOGITS
     poly
    1.05
     поли
    0.96
    Poly
    0.90
     POLY
    0.88
     Poly
    0.87
     ポリ
    0.84
    poly
    0.81
    POLY
    0.80
     polyg
    0.77
     polig
    0.77
    Activations Density 0.052%

    No Known Activations