© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 74841
    Prev
    Next
    INDEX
    Explanations

    strategic plans

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

    animals and strategy

    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
    quinoxalin
    0.57
    ход
    0.55
    корд
    0.51
    }}^{(
    0.49
     வாழைப்பழம்
    0.47
    肋
    0.44
    handel
    0.43
    lebihan
    0.43
    աստ
    0.43
    gador
    0.42
    POSITIVE LOGITS
     strate
    0.54
     strategic
    0.53
     plans
    0.52
     camp
    0.52
     transonic
    0.51
     group
    0.51
    LE
    0.49
     spokes
    0.48
    :>
    0.48
     Nate
    0.47
    Activations Density 0.000%

    No Known Activations