© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 91824
    Prev
    Next
    INDEX
    Explanations

    funny or 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-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
     ਤੁਹਾ
    0.52
     orden
    0.50
    ឡិច
    0.49
     மெட்ரோ
    0.48
    ي
    0.48
    攺
    0.46
     bulletins
    0.46
     banknotes
    0.45
    nYou
    0.45
    瑉
    0.45
    POSITIVE LOGITS
     C
    0.49
     k
    0.45
    if
    0.44
    HH
    0.44
    ansa
    0.44
     God
    0.43
    unculus
    0.43
     K
    0.43
     Java
    0.43
    ,
    0.42
    Activations Density 0.004%

    No Known Activations