© 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. 223455
    Prev
    Next
    INDEX
    Explanations

    common collocations

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

    dynamic change and careful use

    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
    結晶
    0.47
     製品
    0.47
    煥
    0.47
     聞い
    0.46
    確保
    0.45
    ﻪ
    0.45
    ⃞
    0.45
     保護
    0.43
     機能
    0.43
    💹
    0.43
    POSITIVE LOGITS
     other
    0.48
     Democrats
    0.45
     Poetry
    0.44
     traged
    0.43
     Drugs
    0.43
     Comedy
    0.42
     Kurds
    0.41
    weil
    0.41
     Dioc
    0.41
     Opera
    0.41
    Activations Density 0.001%

    No Known Activations