© 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. 212555
    Prev
    Next
    INDEX
    Explanations

    Gaia spacecraft

    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
    ınıza
    0.41
    h
    0.40
    ])
    0.39
    ਦ
    0.38
     nemesis
    0.37
    Mara
    0.36
    nay
    0.35
    Serv
    0.35
    करा
    0.35
    )];
    0.34
    POSITIVE LOGITS
    蕉
    0.45
    荨
    0.41
     sunflowers
    0.38
    禿
    0.38
     Macs
    0.37
     கப்
    0.37
     രാജ
    0.36
    钅
    0.36
    ytuc
    0.36
     čovjek
    0.36
    Activations Density 0.001%

    No Known Activations