© 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. 10760
    Prev
    Next
    INDEX
    Explanations

    commands followed by arguments

    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
    ,
    0.45
    ):
    0.43
    .):
    0.42
    ':
    0.42
    emias
    0.41
    '
    0.41
    )_{(
    0.40
    !),
    0.40
    க்கும்
    0.40
    idge
    0.39
    POSITIVE LOGITS
     ม
    0.49
     然後
    0.47
     \$
    0.46
     mW
    0.46
     warna
    0.45
     paraissent
    0.45
     然后
    0.45
     thePack
    0.42
    ंपरा
    0.42
     दशमलव
    0.41
    Activations Density 0.100%

    No Known Activations