© 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. 8562
    Prev
    Next
    INDEX
    Explanations

    ability to

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

    that must, how to, deeply concerned

    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
     başta
    0.59
     довольно
    0.57
     。
    0.55
    islang
    0.54
     были
    0.52
     havia
    0.52
     VERY
    0.51
     bzw
    0.50
     vrlo
    0.50
     ;
    0.49
    POSITIVE LOGITS
     interdependence
    0.56
     রাষ্ট্রের
    0.54
     التحكم
    0.51
    return
    0.51
    實現
    0.51
    ፈላጊ
    0.50
     liberté
    0.50
     adaptability
    0.50
     സൃഷ്ട
    0.49
     besoin
    0.48
    Activations Density 0.134%

    No Known Activations