© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 47054
    Prev
    Next
    INDEX
    Explanations

    security focused goals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ምልክ
    0.47
     proportion
    0.47
     Osmanlı
    0.47
     પછી
    0.46
    栉
    0.46
     sırasında
    0.45
     thousand
    0.45
     tıkl
    0.45
    照射
    0.45
     入っ
    0.45
    POSITIVE LOGITS
    힙
    0.46
    Creator
    0.46
    à
    0.44
    ultra
    0.43
    bool
    0.42
    ump
    0.42
    pay
    0.41
    py
    0.41
    도
    0.40
    ás
    0.40
    Activations Density 0.005%

    No Known Activations