© 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. 86519
    Prev
    Next
    INDEX
    Explanations

    construction project and MLS Electrosystem

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

    parametric, patients, HTML, brackets

    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
    ene
    0.63
    
    0.51
    laptop
    0.50
    ක්
    0.49
    jarah
    0.49
    lim
    0.49
    ślin
    0.49
    드의
    0.47
    ogn
    0.47
    kla
    0.47
    POSITIVE LOGITS
    }:=\
    0.51
     ফ্যাস
    0.47
     felicit
    0.47
    體驗
    0.47
     beerCount
    0.47
     uitgenodigd
    0.46
    接著
    0.46
    ometries
    0.45
    團隊
    0.45
    倫
    0.45
    Activations Density 0.000%

    No Known Activations