© 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. 243622
    Prev
    Next
    INDEX
    Explanations

    entry into

    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
    стал
    0.43
     نتيجة
    0.43
    ectomy
    0.43
    (.*
    0.42
     ग्रस्त
    0.42
    ໃນ
    0.42
     созна
    0.42
    ياة
    0.42
    効果
    0.41
     currentState
    0.41
    POSITIVE LOGITS
     pelot
    0.47
     tos
    0.43
     가지
    0.43
     홀
    0.41
    ফার
    0.39
     sere
    0.39
     बिर
    0.38
    toadd
    0.38
    Fore
    0.38
     কল
    0.38
    Activations Density 0.001%

    No Known Activations