© 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. 39183
    Prev
    Next
    INDEX
    Explanations

    love affair

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

    "signed" or "based" or "commitment"

    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
    CK
    0.50
    ν
    0.46
    AH
    0.46
    DL
    0.45
    yn
    0.45
    MM
    0.44
    IAN
    0.44
    il
    0.44
    ایی
    0.43
    YAN
    0.43
    POSITIVE LOGITS
     ბ
    0.50
     Bookstore
    0.49
     Ně
    0.48
     Pharmacology
    0.47
     الترم
    0.46
     Hochschule
    0.46
     Discipline
    0.45
     ಇದೆ
    0.45
     宝宝
    0.45
    䚰
    0.45
    Activations Density 0.000%

    No Known Activations