© 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
    2. Gemma-3-27B-IT
    3. 16-GEMMASCOPE-2-RES-262K
    4. 142552
    Prev
    Next
    INDEX
    Explanations

    African American Vernacular English

    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
    ALCHEMY
    0.56
    }*/
    0.55
    ură
    0.55
    🈵
    0.55
    desde
    0.54
     iguais
    0.54
     garanti
    0.54
    KURZ
    0.54
    މ
    0.54
     epiphany
    0.53
    POSITIVE LOGITS
     Built
    0.43
    apport
    0.43
    流
    0.43
    系統
    0.42
    ändig
    0.42
     scouring
    0.40
    B
    0.40
     sympath
    0.40
     GIS
    0.39
     burner
    0.39
    Activations Density 0.000%

    No Known Activations