© 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. 74665
    Prev
    Next
    INDEX
    Explanations

    weakness

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

    weakness

    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
     zapewn
    0.61
    padă
    0.61
     войск
    0.60
     strikers
    0.59
     процессо
    0.58
     дети
    0.57
     힘
    0.57
     wymien
    0.55
     พิจิก
    0.55
     벡터
    0.55
    POSITIVE LOGITS
    弱
    1.01
     weakly
    0.98
     Weak
    0.96
    Weak
    0.91
    弱い
    0.91
    weak
    0.90
     weak
    0.88
     weaker
    0.76
     weakened
    0.75
     lemah
    0.74
    Activations Density 0.010%

    No Known Activations