© 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. 216548
    Prev
    Next
    INDEX
    Explanations

    acquisition, distribute, password, container, Jamaican, Bank

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

    making upgrades

    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
     bodhis
    0.48
    uctive
    0.44
    ún
    0.44
     internos
    0.43
    还需要
    0.42
    炼
    0.42
    riculum
    0.41
    ra
    0.40
    丢
    0.40
    损失
    0.40
    POSITIVE LOGITS
    будь
    0.47
    であ
    0.43
     outweigh
    0.42
     Bluff
    0.41
     graffiti
    0.41
    marquee
    0.40
    絶対に
    0.40
     автомобі
    0.39
     éxito
    0.39
     Казіно
    0.38
    Activations Density 0.000%

    No Known Activations