© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 15452
    Prev
    Next
    INDEX
    Explanations

    closing brace or bracket

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ißler
    0.51
    ają
    0.48
    पाउंड
    0.47
    ೭
    0.47
    
    0.46
    btw
    0.46
    យើង
    0.46
     zatim
    0.46
     })),
    0.46
     %=
    0.45
    POSITIVE LOGITS
    пил
    0.43
    EPEND
    0.42
    一
    0.39
    ORDON
    0.39
    ρι
    0.38
    瓦
    0.38
    披
    0.38
     non
    0.38
    വാൻ
    0.38
     favorite
    0.38
    Activations Density 0.013%

    No Known Activations