© 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. 100576
    Prev
    Next
    INDEX
    Explanations

    collection of clearance necklaces

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

    AWS HA Pair

    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
    蔑
    0.51
    楼主
    0.49
    嵬
    0.48
    VerFile
    0.47
    릴
    0.47
    岧
    0.46
    弹性
    0.46
    까
    0.46
    ема
    0.45
    ื่อน
    0.45
    POSITIVE LOGITS
    Buk
    0.50
     crayfish
    0.49
     known
    0.46
     für
    0.46
    CD
    0.46
    ‌.
    0.46
     governor
    0.46
     bridge
    0.46
    IoT
    0.45
     Falcons
    0.45
    Activations Density 0.000%

    No Known Activations