© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 179136
    Prev
    Next
    INDEX
    Explanations

    MCTS: Windows Server

    np_acts-logits-general · gemini-2.5-flash-lite

    multilingual reasoning and generation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ma
    0.57
    st
    0.53
    th
    0.52
    ::
    0.50
    -
    0.50
    o
    0.50
    ta
    0.49
    Static
    0.48
    a
    0.48
    Task
    0.46
    POSITIVE LOGITS
     conviv
    0.54
    იც
    0.54
     zmniejs
    0.54
    بیه
    0.52
     convain
    0.52
    واق
    0.51
     deluge
    0.51
     inté
    0.50
     seno
    0.49
    নিতে
    0.49
    Activations Density 0.000%

    No Known Activations