© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 210131
    Prev
    Next
    INDEX
    Explanations

    access this

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

    malware types and technical terms

    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
     அவனே
    0.51
     بنیادی
    0.50
     розгля
    0.49
    ︰
    0.49
    śa
    0.48
    𝟬
    0.48
     პროფილი
    0.48
    ๘
    0.48
    𒅴
    0.47
     विवाद
    0.47
    POSITIVE LOGITS
     Erm
    0.48
    ↵
    0.47
     Par
    0.47
     veces
    0.47
     Rats
    0.46
     Bernad
    0.46
     Parsons
    0.44
     Stern
    0.44
     Kos
    0.44
     Rabb
    0.44
    Activations Density 0.000%

    No Known Activations