© 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. 16-GEMMASCOPE-2-RES-262K
    7. 139783
    Prev
    Next
    INDEX
    Explanations

    Cascade, order, Carol, brushes, pen

    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
    xyl
    0.46
    łoży
    0.45
    ských
    0.45
     GDPPC
    0.45
    ぎ
    0.45
     लग्न
    0.44
     عَل
    0.44
     எழுத
    0.43
    ।
    0.43
    úp
    0.43
    POSITIVE LOGITS
     Burns
    0.52
    ви
    0.48
     Racine
    0.46
     Burnu
    0.45
    眽
    0.45
     Julio
    0.44
     Browne
    0.44
     Anatomy
    0.43
     preservar
    0.43
     Jammu
    0.43
    Activations Density 0.000%

    No Known Activations