© 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. 58092
    Prev
    Next
    INDEX
    Explanations

    contained within

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

    absolute position; gap analysis

    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
     دفاتر
    0.48
    Ciudad
    0.46
    翮
    0.44
    ORGE
    0.44
    讹
    0.44
    私募基金管理人
    0.44
    גע
    0.43
    BSData
    0.43
    萏
    0.43
    Qaeda
    0.43
    POSITIVE LOGITS
     lt
    0.57
     conta
    0.57
     Lt
    0.54
     ie
    0.52
     (?,
    0.51
      
    0.50
     cosmetic
    0.49
     Siam
    0.48
     v
    0.48
     ez
    0.48
    Activations Density 0.000%

    No Known Activations