© 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. 64861
    Prev
    Next
    INDEX
    Explanations

    Swans, upregulation, is,

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

    abandoned, neutrality, inequality

    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
     circumst
    0.46
     asynchronously
    0.46
    ధాన
    0.46
    黛
    0.45
    细腻
    0.43
     wydar
    0.42
     Notifications
    0.42
     circulate
    0.41
    लेंट
    0.41
    댕
    0.40
    POSITIVE LOGITS
     সি
    0.49
    redo
    0.49
     spelled
    0.49
     ಗೋ
    0.47
    verted
    0.47
    balo
    0.46
    regen
    0.46
     ಶ್ರೀ
    0.45
     次元
    0.45
     गोवा
    0.45
    Activations Density 0.000%

    No Known Activations