© 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. 11720
    Prev
    Next
    INDEX
    Explanations

    money into future

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

    sequence sequentially

    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
     étamines
    0.46
     phiếu
    0.43
    asmine
    0.42
    ᒍ
    0.42
     antiserum
    0.41
    cadherin
    0.40
     yearn
    0.40
     tyle
    0.40
     குதிக
    0.40
    ♈
    0.40
    POSITIVE LOGITS
     Voici
    0.45
     Vý
    0.45
     Profit
    0.44
     sogenannte
    0.44
     Monday
    0.44
     Would
    0.42
     Restaurant
    0.42
     November
    0.41
     United
    0.41
     September
    0.41
    Activations Density 0.000%

    No Known Activations