© 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. 232261
    Prev
    Next
    INDEX
    Explanations

    they followed by verb

    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
    s
    0.52
     třeba
    0.47
     boundless
    0.46
     handcuffs
    0.44
     bigotry
    0.44
     for
    0.44
    Refreshing
    0.43
     gioco
    0.42
     craftsmanship
    0.42
     napkin
    0.42
    POSITIVE LOGITS
    科学院
    0.55
    ριθ
    0.52
    峣
    0.51
    nilai
    0.48
    婪
    0.46
    льзя
    0.46
    라이
    0.45
     naudoj
    0.45
    ovanie
    0.45
    ometraje
    0.45
    Activations Density 0.001%

    No Known Activations