© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 53-GEMMASCOPE-2-RES-262K
    7. 84889
    Prev
    Next
    INDEX
    Explanations

    computer technology terms

    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_53_width_262k_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
    拔
    0.38
     πρά
    0.38
    <0xBE>
    0.37
     مزاح
    0.36
     hugely
    0.36
     pulling
    0.35
    compliance
    0.35
    dem
    0.35
     compliance
    0.35
     curving
    0.35
    POSITIVE LOGITS
    一条
    0.40
     машина
    0.39
     vistazo
    0.38
     yaad
    0.38
     trink
    0.38
    끼
    0.38
     дети
    0.38
    рея
    0.38
     okt
    0.38
    льній
    0.37
    Activations Density 0.006%

    No Known Activations