© 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. 150408
    Prev
    Next
    INDEX
    Explanations

    first names and last names

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

    she should be unique

    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
    setObjectName
    0.54
    ető
    0.53
    豳
    0.46
    ኑ
    0.45
    라마
    0.44
     الجديد
    0.43
    경제
    0.43
     admet
    0.43
    currentSprite
    0.42
     atthakath
    0.42
    POSITIVE LOGITS
     позволяет
    0.48
    ms
    0.44
     non
    0.44
     participant
    0.43
     permit
    0.42
     你
    0.42
    ON
    0.42
    真
    0.41
     регу
    0.41
     permita
    0.41
    Activations Density 0.002%

    No Known Activations