© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 53428
    Prev
    Next
    INDEX
    Explanations

    bluish through, burns destroy

    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
    への
    0.46
    잦
    0.43
     प्रत्येक
    0.43
    ត្រូ
    0.42
    mdui
    0.42
    subkey
    0.42
    ဩ
    0.41
    لوار
    0.41
    周年
    0.40
    篒
    0.40
    POSITIVE LOGITS
     Cyrus
    0.43
     Hered
    0.40
     charakter
    0.40
     Sys
    0.38
     ولی
    0.38
     Delhi
    0.38
     Bliss
    0.38
     Hope
    0.38
     french
    0.38
     Propri
    0.38
    Activations Density 0.005%

    No Known Activations