© 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. 50317
    Prev
    Next
    INDEX
    Explanations

    years of experience

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

    **8** or **CPU** or **Drill** followed by other text

    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
    t
    0.42
     edited
    0.41
     yang
    0.39
     animate
    0.39
     meniscus
    0.38
    circ
    0.38
     disso
    0.38
     entered
    0.38
     g
    0.37
     t
    0.37
    POSITIVE LOGITS
    uum
    0.50
    Tous
    0.50
    Toplam
    0.49
    鋳
    0.49
    そして
    0.48
    ूरी
    0.48
     liitty
    0.48
    の関係
    0.47
    𝒉
    0.47
    Rece
    0.46
    Activations Density 0.000%

    No Known Activations