© 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. 46812
    Prev
    Next
    INDEX
    Explanations

    endings and outcomes

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

    purpose, Target, Idea, queen, chips

    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
    Ako
    0.47
    יי
    0.46
    PRESENT
    0.45
    נ
    0.45
    ব্র
    0.45
    Ку
    0.43
    Mix
    0.43
    хожу
    0.43
    Кор
    0.43
    往
    0.43
    POSITIVE LOGITS
     ionization
    0.54
     तारा
    0.53
     explanations
    0.52
     tyrosine
    0.52
     สมการ
    0.52
     alcohols
    0.51
     loudspeakers
    0.51
     reiniciar
    0.51
     vibrational
    0.50
     accelerators
    0.50
    Activations Density 0.001%

    No Known Activations