© 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. 189904
    Prev
    Next
    INDEX
    Explanations

    state variations

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

    failing drive, religious freedom, natural gravity

    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
    م
    0.57
    νες
    0.52
    Biden
    0.50
     обеспечения
    0.47
    蛋白質
    0.47
    𝙧
    0.47
     AVAudio
    0.46
    ما
    0.46
    আপনি
    0.46
     rodzaj
    0.46
    POSITIVE LOGITS
     asymptotics
    0.47
     discourse
    0.47
     contrad
    0.46
     lattice
    0.46
     Sü
    0.45
    雅
    0.45
    話を
    0.43
    ].)
    0.43
     स
    0.43
     glass
    0.42
    Activations Density 0.001%

    No Known Activations