© 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. 163551
    Prev
    Next
    INDEX
    Explanations

    warning, required, keeping, none, answer, finish, highest good

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

    swore, smile, oaths, directly, limitation

    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
    膨
    0.53
    📣
    0.53
    ্যারি
    0.48
    ప్ర
    0.47
     remain
    0.46
    道路
    0.45
    annuation
    0.45
    ंकज
    0.45
    挀
    0.44
     निधि
    0.43
    POSITIVE LOGITS
     Пра
    0.52
     θεω
    0.46
     Два
    0.46
    alez
    0.46
     रचना
    0.46
    atro
    0.45
     ಜೀವ
    0.45
     Бу
    0.45
     Մ
    0.45
     pohyb
    0.44
    Activations Density 0.000%

    No Known Activations