© 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. 42196
    Prev
    Next
    INDEX
    Explanations

    introducing explanation or summarization

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

    in simpler terms or basically

    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
     også
    0.54
     cinquième
    0.51
     उल्लेख
    0.50
     mengingat
    0.50
     පිළිබඳ
    0.48
     ankaŭ
    0.48
     −/−
    0.48
     byly
    0.48
     یاد
    0.47
     weiteres
    0.47
    POSITIVE LOGITS
    也就是说
    0.85
    Basically
    0.81
    つまり
    0.79
    Essentially
    0.78
    basically
    0.78
     Basically
    0.78
     basically
    0.75
     Essentially
    0.71
     essentially
    0.70
    :
    0.68
    Activations Density 0.042%

    No Known Activations