© 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. 8426
    Prev
    Next
    INDEX
    Explanations

    make your

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

    probing questions based on answer

    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
    0.56
    Osm
    0.46
    www
    0.45
     Osm
    0.45
     www
    0.41
     most
    0.41
     emails
    0.41
     Devin
    0.41
    ↵↵
    0.40
     neither
    0.40
    POSITIVE LOGITS
     लकार
    0.56
    䤃
    0.55
     見
    0.50
     nacionales
    0.49
    𒁺
    0.49
     করিলেন
    0.48
     đoán
    0.48
     nazionali
    0.48
     arreg
    0.48
     제조
    0.47
    Activations Density 0.000%

    No Known Activations