© 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. 204293
    Prev
    Next
    INDEX
    Explanations

    before diving deep

    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
     firsthand
    0.45
     genome
    0.43
     Sk
    0.43
     根据
    0.43
     repurposed
    0.43
    原则
    0.42
     hallar
    0.41
    腟
    0.41
     요거
    0.40
     kaleidoscopic
    0.40
    POSITIVE LOGITS
    ي
    0.54
    𝚃
    0.48
     осуществля
    0.47
    ం
    0.47
    ри
    0.46
     combina
    0.46
    θε
    0.46
    p
    0.46
     tle
    0.45
    「
    0.45
    Activations Density 0.001%

    No Known Activations