© 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. 3956
    Prev
    Next
    INDEX
    Explanations

    lists, descriptions, and notes

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

    explanations:

    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
    ဈ
    0.24
    border
    0.23
    delta
    0.22
    िंग
    0.22
    value
    0.22
     অঞ্চলে
    0.21
    localScale
    0.21
    width
    0.21
    hü
    0.21
    性和
    0.21
    POSITIVE LOGITS
    ：
    0.32
    ઃ
    0.29
    ៈ
    0.28
    ):
    0.27
    :"
    0.26
    :
    0.26
    :}
    0.25
              
    0.25
            
    0.25
    :",
    0.25
    Activations Density 0.076%

    No Known Activations