© 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. 174694
    Prev
    Next
    INDEX
    Explanations

    our organsdeposits rangegetting bettersay something

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

    data pipelines and ads

    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
    一股
    0.46
    UATION
    0.45
    ᱓
    0.45
     装
    0.44
     carcass
    0.43
     monto
    0.43
    СФ
    0.43
    财
    0.43
     LaserJet
    0.43
     bake
    0.43
    POSITIVE LOGITS
     आश्चर्य
    0.52
    jelen
    0.52
    aines
    0.51
    ഽ
    0.50
    lan
    0.48
    testimon
    0.47
    Defining
    0.46
    stere
    0.46
     നിന്ന്
    0.46
    habitude
    0.45
    Activations Density 0.001%

    No Known Activations