© 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. 1668
    Prev
    Next
    INDEX
    Explanations

    purchase and price

    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
    <0x80>
    0.36
     inescap
    0.36
     inextricably
    0.35
     вследствие
    0.32
    罹
    0.32
     conceivably
    0.31
     unamb
    0.31
    ЕС
    0.30
    -,
    0.29
     사건
    0.29
    POSITIVE LOGITS
     bbq
    0.42
    🥰
    0.39
    ‼️
    0.39
     great
    0.39
     recommande
    0.38
    很好
    0.38
    😍
    0.38
     very
    0.37
     everytime
    0.37
     soooo
    0.37
    Activations Density 0.002%

    No Known Activations