© 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. 208807
    Prev
    Next
    INDEX
    Explanations

    metro line, 80%, Service, crowns

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

    asking for definitions or terms

    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
     izinsuku
    0.51
    i
    0.47
    fuel
    0.46
    lightbox
    0.46
    full
    0.44
    flood
    0.44
    LIGHT
    0.44
    fib
    0.43
     ताजा
    0.43
    brown
    0.43
    POSITIVE LOGITS
    辭
    0.51
    ጠቀ
    0.44
    })$.
    0.44
     함
    0.44
    耍
    0.43
    였다
    0.43
    鬥
    0.43
    يديو
    0.42
     laziness
    0.42
     Forschung
    0.41
    Activations Density 0.000%

    No Known Activations