© 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. 31-GEMMASCOPE-2-RES-65K
    4. 3298
    Prev
    Next
    INDEX
    Explanations

    fading, flicker, spark

    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_65k_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
    i
    0.53
    Bh
    0.50
     ہوگا
    0.48
    дом
    0.46
     Durga
    0.46
    为您
    0.46
     labb
    0.45
    薷
    0.45
    im
    0.44
    Config
    0.44
    POSITIVE LOGITS
     marital
    0.49
    세계
    0.49
     internationally
    0.45
    妻
    0.45
    </em>
    0.43
     televisions
    0.43
     siè
    0.43
     pharmaceuticals
    0.43
    ।”
    0.42
     svjets
    0.42
    Activations Density 0.001%

    No Known Activations