© 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. 191954
    Prev
    Next
    INDEX
    Explanations

    numbers and non-English words

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

    botnet

    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
     B
    0.64
     O
    0.63
     W
    0.63
     E
    0.62
    0.62
     Man
    0.61
     H
    0.60
     D
    0.59
     Y
    0.59
     Men
    0.59
    POSITIVE LOGITS
    anath
    0.61
    ௦
    0.58
     वर्कशीट
    0.57
     મહિના
    0.57
     નં
    0.56
    그램
    0.55
     ተጨማሪ
    0.55
     નંબર
    0.55
     ቀለም
    0.55
     школы
    0.55
    Activations Density 0.002%

    No Known Activations