© 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. 191285
    Prev
    Next
    INDEX
    Explanations

    legal and specific terms

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

    parry, secret, reusable code

    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
     ஆண்டுகள்
    0.46
    ίναι
    0.45
     そして
    0.44
     कब
    0.44
    ancements
    0.43
     suppressing
    0.43
    transferases
    0.43
     փ
    0.42
    จะ
    0.42
    ientôt
    0.42
    POSITIVE LOGITS
     iets
    0.47
     IME
    0.46
     Alber
    0.45
     Sonny
    0.44
    šić
    0.43
    本文
    0.43
    Sis
    0.43
     verein
    0.42
     coleção
    0.42
     Gian
    0.42
    Activations Density 0.004%

    No Known Activations