© 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. 105785
    Prev
    Next
    INDEX
    Explanations

    closing phrases and sign-offs

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

    staying current; specific

    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
    治疗
    0.50
    得以
    0.49
    
    0.46
    т
    0.46
     Regul
    0.45
     mobilization
    0.43
     therapy
    0.42
     терапии
    0.42
     impor
    0.42
    维修
    0.41
    POSITIVE LOGITS
     遅く
    0.54
    isFullscreen
    0.48
    neighbours
    0.48
    seer
    0.47
    icals
    0.47
    흄
    0.46
    ᄍ
    0.46
    naam
    0.46
     carbides
    0.46
     staggering
    0.45
    Activations Density 0.000%

    No Known Activations