© 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. 125377
    Prev
    Next
    INDEX
    Explanations

    you know that/you/the/how/what

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

    phrases starting with 'you know'

    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
     понимать
    0.47
    ंती
    0.44
     навыки
    0.44
     конференции
    0.42
     ज्यादातर
    0.42
    ণীর
    0.42
    使用的是
    0.42
    胱
    0.41
     tergantung
    0.40
     कभी
    0.40
    POSITIVE LOGITS
    ă
    0.44
    okkal
    0.43
    <0x0D>
    0.42
     zde
    0.39
    節目
    0.39
     promissory
    0.38
    بن
    0.38
     promis
    0.38
    ificação
    0.38
    總
    0.38
    Activations Density 0.008%

    No Known Activations