© 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. 99657
    Prev
    Next
    INDEX
    Explanations

    spark, racing, scents

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

    note that

    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
    jima
    0.48
     神
    0.43
     秒
    0.42
     Joon
    0.42
    .”)
    0.42
     sunk
    0.42
     kidnap
    0.41
     menyiapkan
    0.41
     इफ
    0.41
     Stefano
    0.41
    POSITIVE LOGITS
    كر
    0.52
    ا
    0.52
    ستا
    0.50
    ต่ำ
    0.49
    Person
    0.47
    ða
    0.46
    са
    0.46
    ابل
    0.46
    راع
    0.45
    වත
    0.45
    Activations Density 0.001%

    No Known Activations