© 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. 183642
    Prev
    Next
    INDEX
    Explanations

    online casino gambling

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

    reverse order of alphabet

    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
     Webb
    0.48
    nemen
    0.48
     =\
    0.46
     وَ
    0.45
     కావ
    0.44
     プ
    0.42
     objek
    0.42
    攢
    0.42
    爫
    0.41
    Prin
    0.41
    POSITIVE LOGITS
     financed
    0.54
    aways
    0.47
     immigrated
    0.47
    BA
    0.47
     instantly
    0.46
    ຕ້ອງການ
    0.46
     intermittently
    0.46
     clever
    0.45
     instilled
    0.45
     installers
    0.44
    Activations Density 0.001%

    No Known Activations