© 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. 15603
    Prev
    Next
    INDEX
    Explanations

    features and benefits

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

    bullet points; lists; examples

    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
    tLogRow
    0.43
    ᒧ
    0.43
     మన
    0.42
    滀
    0.42
     fiasco
    0.40
     consiglio
    0.40
    bottlecap
    0.39
     taco
    0.38
    ুতের
    0.38
     نت
    0.38
    POSITIVE LOGITS
    •
    0.96
    <ul>
    0.82
     •
    0.79
    
    0.77
    ⦁
    0.67
    ①
    0.66
    ✔
    0.66
     
    0.65
    ✅
    0.64
     ・
    0.63
    Activations Density 0.031%

    No Known Activations