© 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. 1564
    Prev
    Next
    INDEX
    Explanations

    frequency or occurrence

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

    explanations following actions

    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
    *
    0.45
     postwar
    0.42
     সেসব
    0.38
    全新
    0.37
     years
    0.36
    之类的
    0.36
     Plan
    0.36
     sämt
    0.36
    ></
    0.36
     προϊόν
    0.36
    POSITIVE LOGITS
     Sometimes
    0.54
     иногда
    0.52
     دعوت
    0.52
     мама
    0.51
     oftentimes
    0.51
     Often
    0.51
     manchmal
    0.51
     लढ
    0.50
    鼓勵
    0.50
    ampaikan
    0.50
    Activations Density 0.001%

    No Known Activations