© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 9496
    Prev
    Next
    INDEX
    Explanations

    starting or backdrop

    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
     playlists
    0.42
     ആണ
    0.41
     लेनदेन
    0.37
     sniper
    0.37
     careless
    0.37
     পুরুষ
    0.37
     ইহা
    0.37
    侕
    0.37
     sporadic
    0.36
     momentary
    0.36
    POSITIVE LOGITS
    题材
    0.43
    導入
    0.39
     выбрать
    0.38
    ⺌
    0.38
    starting
    0.38
    Instead
    0.37
     fewer
    0.37
    focus
    0.37
     backdrop
    0.36
    scape
    0.36
    Activations Density 0.123%

    No Known Activations