© 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. 132495
    Prev
    Next
    INDEX
    Explanations

    also survived by

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

    mommmy girlfriend

    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
     doctrines
    0.46
     baratos
    0.46
     Strikes
    0.45
     इसलिए
    0.45
     strikes
    0.43
    }}=-\
    0.43
    Dlg
    0.41
     inodes
    0.41
     !=
    0.41
    だと思います
    0.40
    POSITIVE LOGITS
     સહ
    0.52
     współpracy
    0.49
    শিষ্ট
    0.48
    Active
    0.48
    总量
    0.48
     momenti
    0.46
    更
    0.46
    获奖
    0.46
     আরও
    0.46
    ότερα
    0.46
    Activations Density 0.001%

    No Known Activations