© 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. 196712
    Prev
    Next
    INDEX
    Explanations

    messages sponsors saving blood threatens offspring famous

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

    shop floor data

    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
     remodeling
    0.51
     $\|\
    0.45
     teorema
    0.45
     deductive
    0.45
     inferences
    0.44
     antidepressant
    0.44
     ዓይነ
    0.43
     >>
    0.42
     meilleure
    0.42
     employé
    0.42
    POSITIVE LOGITS
    რ
    0.50
    Г
    0.50
    渍
    0.49
    nx
    0.48
    廝
    0.47
    Hunt
    0.47
    到位
    0.47
    ítása
    0.46
    stre
    0.46
    Д
    0.46
    Activations Density 0.000%

    No Known Activations