© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 162101
    Prev
    Next
    INDEX
    Explanations

    concept of

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

    you ask to explain

    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
     Ausnahme
    0.51
     Blogging
    0.47
     Attitudes
    0.46
     تنظيم
    0.46
    拧
    0.46
     lèvres
    0.45
     эксплуа
    0.44
     சர்ச்ச
    0.44
    大大
    0.43
     guitarra
    0.43
    POSITIVE LOGITS
    k
    0.51
    คืน
    0.48
     di
    0.47
    kiego
    0.47
     C
    0.46
    agt
    0.46
    tgt
    0.45
    ว่า
    0.44
     usia
    0.43
     debtor
    0.42
    Activations Density 0.001%

    No Known Activations