© 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. 40-GEMMASCOPE-2-RES-262K
    7. 31002
    Prev
    Next
    INDEX
    Explanations

    aspect ratio

    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_40_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
     architect
    0.40
    ード
    0.38
     Архи
    0.38
    Arch
    0.37
     મે
    0.37
    eu
    0.37
    氈
    0.37
    πλ
    0.36
    ומ
    0.36
     архі
    0.36
    POSITIVE LOGITS
    borist
    0.44
    ping
    0.43
     Arlington
    0.42
     الار
    0.42
    rear
    0.40
    Sally
    0.40
     ar
    0.39
    Ar
    0.39
     borrar
    0.39
     بیچ
    0.39
    Activations Density 0.007%

    No Known Activations