© 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. 121559
    Prev
    Next
    INDEX
    Explanations

    Prices are, secretly informed, had more, may or

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

    relationship success or failure

    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
     훨씬
    0.53
    Transaksi
    0.46
    Overlay
    0.44
    近く
    0.44
    世界
    0.43
    飥
    0.43
     Stadt
    0.43
    軎
    0.43
    洊
    0.43
    堌
    0.43
    POSITIVE LOGITS
    wtf
    0.55
     playmaker
    0.53
    у
    0.47
     completions
    0.47
     throttling
    0.47
    marshal
    0.47
     clogged
    0.47
     stunted
    0.47
     failure
    0.46
     filming
    0.46
    Activations Density 0.001%

    No Known Activations