© 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-16K
    7. 5253
    Prev
    Next
    INDEX
    Explanations

    line and linear concepts

    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_16k_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
    d
    0.97
    to
    0.94
    л
    0.92
    di
    0.75
    dan
    0.74
    t
    0.73
    д
    0.71
    '
    0.70
    name
    0.70
    la
    0.68
    POSITIVE LOGITS
     line
    0.97
     Line
    0.88
     lines
    0.86
     خط
    0.86
    LINES
    0.84
     ライン
    0.84
     Lines
    0.82
     линии
    0.82
     الخط
    0.80
     लाइन
    0.80
    Activations Density 0.310%

    No Known Activations