© 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. 22116
    Prev
    Next
    INDEX
    Explanations

    introduces explanations or lists

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

    introducing explanations or lists

    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
     folgenden
    0.57
    以下的
    0.52
    /
    0.52
     التالية
    0.50
     Thornton
    0.50
                  
    0.49
    Ile
    0.47
                       
    0.47
    Who
    0.47
    urm
    0.47
    POSITIVE LOGITS
     fronte
    0.49
    ۔
    0.47
    ாமல்
    0.45
     раздел
    0.45
     downregulation
    0.45
    った
    0.45
     рус
    0.45
    dzić
    0.44
     чле
    0.44
     חו
    0.44
    Activations Density 0.003%

    No Known Activations