© 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. 125627
    Prev
    Next
    INDEX
    Explanations

    online, secret, hidden, details

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

    code whisperer

    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
     fag
    0.46
     উদ্বাস্তু
    0.44
    h
    0.43
     parl
    0.43
     щоб
    0.42
     บ้าน
    0.42
     rebellion
    0.42
     saloon
    0.42
    สนามกีฬา
    0.42
     গণ
    0.41
    POSITIVE LOGITS
    жные
    0.48
    のス
    0.46
    ರ
    0.45
     bhfu
    0.44
    ຈັດສົ່ງ
    0.44
    認定
    0.43
    जेस
    0.43
    ępu
    0.43
    alphas
    0.42
    ļa
    0.42
    Activations Density 0.001%

    No Known Activations