© 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. 127941
    Prev
    Next
    INDEX
    Explanations

    legal cases, marriage, preparation

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

    control or guide

    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
     lä
    0.51
     เป
    0.48
    laus
    0.47
    參数
    0.46
    മാക
    0.46
    祿
    0.46
    bestand
    0.45
    Ș
    0.45
    rieg
    0.45
    disciplinary
    0.44
    POSITIVE LOGITS
     څر
    0.58
    0.52
     USART
    0.48
    0.46
    ucional
    0.45
     unsightly
    0.44
    ர்ஸ்
    0.44
     TIPS
    0.43
     Evernote
    0.43
     znovu
    0.43
    Activations Density 0.001%

    No Known Activations