© 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. 16592
    Prev
    Next
    INDEX
    Explanations

    sentence endings

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

    following `should` or `walk`

    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
    фа
    0.43
    >-</
    0.42
    โม
    0.42
    逶
    0.41
    모
    0.40
    오
    0.39
     фа
    0.39
    кта
    0.39
     picnics
    0.38
    ཥ
    0.38
    POSITIVE LOGITS
     Notably
    0.48
     کردیا
    0.41
     imparted
    0.41
     forze
    0.39
    infused
    0.38
    を用いて
    0.38
     نیرو
    0.38
     hadn
    0.37
     continuando
    0.37
     лиде
    0.37
    Activations Density 0.055%

    No Known Activations