© 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. 126493
    Prev
    Next
    INDEX
    Explanations

    strike at, month highest, therefore that, recommend budgeting, planes globally

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

    stereotypes, harmful phrases

    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
      
    0.55
    À
    0.51
    𝒂
    0.45
     cardiovascular
    0.43
     caffeine
    0.43
    াদন
    0.42
    à
    0.42
     worlds
    0.40
     cerv
    0.40
    ACON
    0.40
    POSITIVE LOGITS
     হচ্ছিল
    0.52
     колеба
    0.48
     डिवीजन
    0.46
    かった
    0.46
    numericUpDown
    0.45
     институт
    0.45
    jobNumber
    0.44
    ifax
    0.44
    ത്തക
    0.44
    ㄼ
    0.44
    Activations Density 0.001%

    No Known Activations