© 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. 123983
    Prev
    Next
    INDEX
    Explanations

    SAF Blend, Palindrome Properties

    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
     vodka
    0.49
     ဒီ
    0.48
    ೂ
    0.47
     comunicaciones
    0.46
    eday
    0.45
    ቷ
    0.43
     sarkar
    0.43
     komunikasi
    0.42
    ഹ്ലാ
    0.42
    𝒾
    0.42
    POSITIVE LOGITS
    教学
    0.47
     antérieure
    0.46
    前
    0.43
     permettre
    0.42
     ống
    0.42
    '):
    0.42
    崁
    0.42
    异常
    0.41
    的
    0.41
     erreur
    0.41
    Activations Density 0.004%

    No Known Activations