© 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-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 7451
    Prev
    Next
    INDEX
    Explanations

    programming identifiers and operators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    фесси
    0.46
     Biennale
    0.46
     Tarifi
    0.43
    ﺴ
    0.43
     conteú
    0.42
    ﺘ
    0.40
     Redmi
    0.38
    mercial
    0.38
     Parlement
    0.38
    োলজি
    0.38
    POSITIVE LOGITS
    י
    0.47
     salute
    0.42
    ко
    0.42
    1
    0.42
    ور
    0.41
    정
    0.40
    লা
    0.40
    ન
    0.40
    ৰ
    0.39
    ল
    0.39
    Activations Density 0.454%

    No Known Activations