© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 240598
    Prev
    Next
    INDEX
    Explanations

    certificate issued

    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
    接过
    0.48
     unloaded
    0.46
     conceding
    0.45
    di
    0.44
     dampen
    0.43
    主に
    0.43
    纫
    0.43
    在
    0.42
     concede
    0.42
    ंशिक
    0.42
    POSITIVE LOGITS
     manchmal
    0.55
     月
    0.48
     
    0.47
     Darstellung
    0.47
     tiem
    0.46
     kỳ
    0.46
     manier
    0.46
     完成
    0.46
     morate
    0.46
     計
    0.46
    Activations Density 0.001%

    No Known Activations