© 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-262K
    4. 138321
    Prev
    Next
    INDEX
    Explanations

    key differences and importance

    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
    猖
    0.45
    Buy
    0.43
    ᱔
    0.42
    )=-\
    0.42
     エネルギー
    0.42
    Sensitive
    0.42
    Burn
    0.41
    વતી
    0.41
    ऱ्यावर
    0.41
    vill
    0.39
    POSITIVE LOGITS
    ↵
    0.52
    '
    0.50
     carat
    0.48
     had
    0.47
     kuh
    0.47
    లను
    0.46
     sosyal
    0.45
     amino
    0.45
    తో
    0.45
     tạo
    0.44
    Activations Density 0.001%

    No Known Activations