© 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. 200175
    Prev
    Next
    INDEX
    Explanations

    forex brokers or currency exchange

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

    illegal, early, familiar contexts

    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
    ותר
    0.46
    цен
    0.46
     Bavaria
    0.45
    asting
    0.45
    Band
    0.45
    ,
    0.44
    Campaign
    0.42
    ]}$
    0.42
    控え
    0.42
    houette
    0.41
    POSITIVE LOGITS
     ຂ
    0.53
     справед
    0.53
    蟎
    0.53
     причинам
    0.52
     nút
    0.52
    按钮
    0.50
    isak
    0.50
     ઉપયોગ
    0.49
     ইলেক্ট
    0.48
     虽然
    0.48
    Activations Density 0.000%

    No Known Activations