© 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. 233007
    Prev
    Next
    INDEX
    Explanations

    worldwide screening, Surface Go, integrated pressure

    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
     simplesmente
    0.54
     rezultat
    0.48
    奔
    0.48
    ソッド
    0.48
     aparentemente
    0.48
    𝓶
    0.47
    א
    0.46
     analis
    0.46
     atualmente
    0.46
    方法的
    0.46
    POSITIVE LOGITS
     Continue
    0.55
    ෙකු
    0.49
     sold
    0.49
     Anwar
    0.48
     hairdryer
    0.48
    yd
    0.47
     స్ట
    0.47
     Nai
    0.47
     Մ
    0.46
     Duan
    0.46
    Activations Density 0.000%

    No Known Activations