© 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. 208594
    Prev
    Next
    INDEX
    Explanations

    financial assets, wedding, and ransomware

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

    vanishing/exploding gradients

    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
     IHDA
    0.51
    展開
    0.48
     kiddos
    0.46
    Madam
    0.45
    ᅴ
    0.45
    نج
    0.44
     fanbase
    0.44
    ᅪ
    0.43
    創新
    0.42
    ICHIGAN
    0.42
    POSITIVE LOGITS
    тони
    0.57
     gradually
    0.49
    decrease
    0.48
    ников
    0.47
    oasis
    0.45
     Although
    0.45
     ajust
    0.45
    ার
    0.43
    ptus
    0.43
    reduced
    0.43
    Activations Density 0.000%

    No Known Activations