© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 7388
    Prev
    Next
    INDEX
    Explanations

    and complete, didn, give, warm, tried

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <0xBF>
    0.29
              
    0.28
     Nonlinear
    0.25
    <0xBD>
    0.25
                     
    0.25
     thereof
    0.25
                              
    0.23
    ↓↓
    0.23
    े
    0.23
    ↵
    0.23
    POSITIVE LOGITS
     trochę
    0.37
     약간
    0.34
     trochu
    0.34
     also
    0.33
     algunas
    0.33
    Tenemos
    0.32
     imaju
    0.32
    也有
    0.31
     coś
    0.31
     there
    0.31
    Activations Density 0.477%

    No Known Activations