© 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. 57721
    Prev
    Next
    INDEX
    Explanations

    He likes, Let’s

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

    animals and technical terms

    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
    MktCap
    0.52
     integrante
    0.51
     saling
    0.51
    abdominal
    0.50
    .`
    0.48
     Kembali
    0.47
     이용하여
    0.47
    intégration
    0.46
    คืน
    0.46
    PlatformImage
    0.45
    POSITIVE LOGITS
    的主要
    0.46
    Formatted
    0.43
     Chowdhury
    0.43
     চৌধুরী
    0.40
     যোগ্য
    0.39
     Sánchez
    0.39
    先生
    0.39
    猫
    0.39
     Chor
    0.38
    درسة
    0.38
    Activations Density 0.000%

    No Known Activations