© 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. 133331
    Prev
    Next
    INDEX
    Explanations

    service centre activity

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

    preserving important equations and bases

    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
    张
    0.62
    对
    0.61
    父
    0.56
    师
    0.56
    ใช้
    0.54
    ΟΣ
    0.54
    时
    0.54
    罗
    0.53
    장
    0.53
    官网
    0.51
    POSITIVE LOGITS
     pernicious
    0.58
     nucleic
    0.58
     contagion
    0.56
     delusions
    0.55
     histological
    0.54
     incompre
    0.54
     genomes
    0.54
     inasmuch
    0.53
     cardia
    0.53
    dell
    0.52
    Activations Density 0.001%

    No Known Activations