© 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. 208679
    Prev
    Next
    INDEX
    Explanations

    For example

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

    what happens if

    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
    Ты
    0.54
    Те
    0.52
    Ин
    0.50
    아야
    0.46
    юць
    0.46
    Ди
    0.45
    кта
    0.45
    않
    0.44
    배
    0.44
    Да
    0.44
    POSITIVE LOGITS
     o
    0.56
     sukses
    0.56
     carousel
    0.50
    渤
    0.49
     shenanigans
    0.48
     rooster
    0.48
     scallop
    0.47
     boa
    0.47
     bouillon
    0.47
     roast
    0.46
    Activations Density 0.000%

    No Known Activations