© 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. 178724
    Prev
    Next
    INDEX
    Explanations

    funds, investments, jobs

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

    Olive Oil, layer, Calculate, EN

    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
    厕
    0.53
     হইলাম
    0.47
     согласно
    0.44
     রহিল
    0.44
     avevano
    0.44
     metropolis
    0.42
     கொண்டிருந்த
    0.42
     两
    0.41
    赌
    0.41
    িয়াছিল
    0.41
    POSITIVE LOGITS
     investments
    0.46
     lente
    0.46
     subv
    0.45
    さん
    0.43
     darn
    0.42
     actions
    0.42
     fuels
    0.42
     trillions
    0.42
     jobs
    0.42
     taxed
    0.41
    Activations Density 0.000%

    No Known Activations