© 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-16K
    7. 13131
    Prev
    Next
    INDEX
    Explanations

    preventing negative outcomes

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

    excessive negative states

    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_16k_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
     Bukan
    0.53
     bukan
    0.48
    ไม่ใช่
    0.43
    -;
    0.42
     ليس
    0.41
    𝙉
    0.41
    ிருந்த
    0.39
    abhuto
    0.39
    ጧ
    0.38
     使っ
    0.38
    POSITIVE LOGITS
     inadvert
    0.53
     żad
    0.52
     inadvertently
    0.47
     undue
    0.46
     veya
    0.46
     ہونے
    0.46
     evitando
    0.45
     إدارة
    0.44
     unduly
    0.44
     précieux
    0.44
    Activations Density 0.263%

    No Known Activations