© 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-65K
    7. 53768
    Prev
    Next
    INDEX
    Explanations

    carbon atom, tiny cabins, mins/day

    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
    다
    0.50
    '
    0.43
    ха
    0.42
    raž
    0.42
    р
    0.41
    AMG
    0.41
    zuki
    0.41
    х
    0.41
    ელი
    0.40
    нти
    0.40
    POSITIVE LOGITS
     τρό
    0.52
    Off
    0.49
     λέ
    0.48
     cheated
    0.48
    自带
    0.48
     ব্লক
    0.47
     οργαν
    0.47
    Position
    0.46
     పుస్త
    0.46
    IsNull
    0.45
    Activations Density 0.012%

    No Known Activations