© 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. 148436
    Prev
    Next
    INDEX
    Explanations

    new era, joint venture, recovered materials

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

    return or each

    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
     수정
    0.55
     अकॉर्डिंग
    0.52
     秦
    0.51
    娍
    0.50
     각각
    0.49
     욕
    0.49
     多く
    0.48
     나서
    0.47
     ალ
    0.47
     Ily
    0.47
    POSITIVE LOGITS
    ضو
    0.50
    ंजी
    0.48
    with
    0.47
     devices
    0.46
    reate
    0.45
     booklets
    0.44
    devices
    0.44
    দি
    0.42
    اش
    0.42
     offsets
    0.42
    Activations Density 0.001%

    No Known Activations