© 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. 231178
    Prev
    Next
    INDEX
    Explanations

    stock prices and costs

    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
     పరీ
    0.45
    雅黑
    0.45
    GAM
    0.44
     병
    0.44
    Pregnant
    0.43
    纭
    0.43
    ium
    0.43
    ឈ្មោះ
    0.43
    Chain
    0.42
    和服务
    0.42
    POSITIVE LOGITS
    又要
    0.48
    اج
    0.47
     Repar
    0.47
    س
    0.47
     racism
    0.46
    らなかった
    0.44
     democr
    0.44
    𝟎
    0.44
     towards
    0.42
     respecto
    0.42
    Activations Density 0.000%

    No Known Activations