© 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. 98438
    Prev
    Next
    INDEX
    Explanations

    employment

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

    invent detail changing Energy screens

    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
     resignation
    0.49
     equivari
    0.48
    コー
    0.46
     IPython
    0.46
    クー
    0.46
     labb
    0.46
    ্যা
    0.45
    ﮕ
    0.45
    िक्
    0.44
     લે
    0.44
    POSITIVE LOGITS
    tsó
    0.54
    0.47
    spicuous
    0.46
    Starts
    0.46
    starts
    0.46
    ms
    0.45
    ts
    0.45
    ět
    0.44
     hoved
    0.43
    jem
    0.43
    Activations Density 0.001%

    No Known Activations